Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1238 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.5181. Min Act: -0.1700
Data Index: 8117439 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.4243. Min Act: -0.1700
Data Index: 4551485 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3283759 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2681. Min Act: -0.1700
Data Index: 1700176 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2681. Min Act: -0.1700
Data Index: 7420668 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3467046 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2368. Min Act: -0.1700
Data Index: 196723 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.3306. Min Act: -0.1700
Data Index: 5824274 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2056. Min Act: -0.1700
Data Index: 325713 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2056. Min Act: -0.1700
Data Index: 3050406 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2056. Min Act: -0.1700
Data Index: 2087653 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2368. Min Act: -0.1700
Data Index: 6707186 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2056. Min Act: -0.1700
Data Index: 1700168 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2056. Min Act: -0.1700
Data Index: 4551477 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.1743. Min Act: -0.1700
Data Index: 4636812 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.1743. Min Act: -0.1700
Data Index: 5599443 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.1743. Min Act: -0.1700
Data Index: 1122985 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2056. Min Act: -0.1700
Data Index: 2987371 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.1743. Min Act: -0.1700
Data Index: 2176446 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5181. Min Range: -5.5181
Max Act: 5.2056. Min Act: -0.1700
Data Index: 5757638 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19