Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.6166. Min Act: -0.1700
Data Index: 8302496 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.5070. Min Act: -0.1700
Data Index: 286221 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4600. Min Act: -0.1697
Data Index: 6550961 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4443. Min Act: -0.1700
Data Index: 286220 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4443. Min Act: -0.1700
Data Index: 6199135 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4130. Min Act: -0.1700
Data Index: 2126974 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.4130. Min Act: -0.1700
Data Index: 7254224 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3816. Min Act: -0.1700
Data Index: 184607 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3816. Min Act: -0.1700
Data Index: 4657652 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3816. Min Act: -0.1700
Data Index: 7192410 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3973. Min Act: -0.1700
Data Index: 6822175 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3659. Min Act: -0.1700
Data Index: 1557111 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3345. Min Act: -0.1700
Data Index: 2199517 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3345. Min Act: -0.1699
Data Index: 7192406 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3188. Min Act: -0.1700
Data Index: 2230924 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3188. Min Act: -0.1700
Data Index: 1287265 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3345. Min Act: -0.1700
Data Index: 1777648 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3032. Min Act: -0.1700
Data Index: 2864413 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3032. Min Act: -0.1700
Data Index: 1287277 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6166. Min Range: -3.6166
Max Act: 3.3032. Min Act: -0.1700
Data Index: 7192405 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19