Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.6815. Min Act: -0.1700
Data Index: 4318614 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.6033. Min Act: -0.1700
Data Index: 3834312 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.4623. Min Act: -0.1700
Data Index: 7953796 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.4780. Min Act: -0.1700
Data Index: 1531679 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.4310. Min Act: -0.1700
Data Index: 5766639 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3996. Min Act: -0.1700
Data Index: 7371922 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3840. Min Act: -0.1700
Data Index: 5783053 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.4467. Min Act: -0.1700
Data Index: 4134751 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.4153. Min Act: -0.1700
Data Index: 4174114 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3840. Min Act: -0.1700
Data Index: 6741924 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3683. Min Act: -0.1700
Data Index: 1780427 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3212. Min Act: -0.1700
Data Index: 7063146 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.4310. Min Act: -0.1700
Data Index: 5365068 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3212. Min Act: -0.1700
Data Index: 6382692 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3526. Min Act: -0.1700
Data Index: 7931502 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3055. Min Act: -0.1700
Data Index: 6936156 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3055. Min Act: -0.1700
Data Index: 2452987 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3369. Min Act: -0.1700
Data Index: 3861195 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.2741. Min Act: -0.1700
Data Index: 7118014 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6815. Min Range: -3.6815
Max Act: 3.3683. Min Act: -0.1700
Data Index: 7578273 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19