Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1166. Min Range: -7.1166
Max Act: 7.1166. Min Act: -0.1700
Data Index: 6192111 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.8666. Min Act: -0.1700
Data Index: 6233377 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.6478. Min Act: -0.1700
Data Index: 7086168 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.6791. Min Act: -0.1700
Data Index: 4651552 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.5541. Min Act: -0.1700
Data Index: 7706844 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.5228. Min Act: -0.1700
Data Index: 8263994 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.4916. Min Act: -0.1700
Data Index: 7172302 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3978. Min Act: -0.1700
Data Index: 2985812 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.4603. Min Act: -0.1700
Data Index: 464203 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.4603. Min Act: -0.1700
Data Index: 7447376 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3978. Min Act: -0.1700
Data Index: 5378436 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3978. Min Act: -0.1700
Data Index: 2211775 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3666. Min Act: -0.1700
Data Index: 1605980 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3666. Min Act: -0.1700
Data Index: 1350703 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3666. Min Act: -0.1700
Data Index: 4651953 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3353. Min Act: -0.1700
Data Index: 2599486 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.2728. Min Act: -0.1700
Data Index: 6466510 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.2728. Min Act: -0.1700
Data Index: 3732702 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.3041. Min Act: -0.1700
Data Index: 1789424 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1166. Min Range: -7.1166
Max Act: 6.2728. Min Act: -0.1700
Data Index: 8158490 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19