Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1534 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.7226. Min Act: -0.1700
Data Index: 7734829 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.5976. Min Act: -0.1700
Data Index: 152651 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.6289. Min Act: -0.1700
Data Index: 5620215 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.5664. Min Act: -0.1700
Data Index: 4129204 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.5039. Min Act: -0.1700
Data Index: 4296789 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.4101. Min Act: -0.1700
Data Index: 7691825 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.4101. Min Act: -0.1700
Data Index: 8334981 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.4414. Min Act: -0.1700
Data Index: 5828555 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.3789. Min Act: -0.1700
Data Index: 5524046 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.4101. Min Act: -0.1700
Data Index: 6105481 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.3476. Min Act: -0.1700
Data Index: 1709411 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.3164. Min Act: -0.1700
Data Index: 8561550 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2851. Min Act: -0.1700
Data Index: 7958808 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2539. Min Act: -0.1700
Data Index: 2102895 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2539. Min Act: -0.1700
Data Index: 2503782 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2539. Min Act: -0.1700
Data Index: 3822477 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2539. Min Act: -0.1700
Data Index: 8228190 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2851. Min Act: -0.1700
Data Index: 1186167 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2539. Min Act: -0.1700
Data Index: 1362977 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7226. Min Range: -6.7226
Max Act: 6.2539. Min Act: -0.1700
Data Index: 5302464 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19