Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.4203. Min Range: -11.4203
Max Act: 11.4203. Min Act: -0.1700
Data Index: 3356001 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4203. Min Range: -11.4203
Max Act: 11.2328. Min Act: -0.1700
Data Index: 8138198 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.9828. Min Act: -0.1700
Data Index: 8808018 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.8578. Min Act: -0.1700
Data Index: 456560 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.9203. Min Act: -0.1700
Data Index: 2281368 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.7953. Min Act: -0.1700
Data Index: 3299439 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.8578. Min Act: -0.1700
Data Index: 1802496 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.7328. Min Act: -0.1700
Data Index: 3579388 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.7953. Min Act: -0.1700
Data Index: 7158071 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.6703. Min Act: -0.1700
Data Index: 8190004 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.3578. Min Act: -0.1700
Data Index: 3896101 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.2328. Min Act: -0.1700
Data Index: 5860140 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.2328. Min Act: -0.1700
Data Index: 3604937 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.1703. Min Act: -0.1700
Data Index: 5851052 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.0453. Min Act: -0.1700
Data Index: 6814988 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.0453. Min Act: -0.1700
Data Index: 8138199 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.0453. Min Act: -0.1700
Data Index: 6840953 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4203. Min Range: -11.4203
Max Act: 10.0453. Min Act: -0.1700
Data Index: 6209828 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4203. Min Range: -11.4203
Max Act: 9.9828. Min Act: -0.1700
Data Index: 7414456 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4203. Min Range: -11.4203
Max Act: 9.9203. Min Act: -0.1700
Data Index: 7082862 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19