Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.8972. Min Act: -0.1700
Data Index: 8069563 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.6472. Min Act: -0.1700
Data Index: 6047833 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.6784. Min Act: -0.1700
Data Index: 162503 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.6159. Min Act: -0.1700
Data Index: 249750 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.6159. Min Act: -0.1700
Data Index: 5852073 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.5534. Min Act: -0.1700
Data Index: 4444931 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.5222. Min Act: -0.1700
Data Index: 2085909 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.5222. Min Act: -0.1700
Data Index: 6374854 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.5222. Min Act: -0.1700
Data Index: 5469508 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.5222. Min Act: -0.1700
Data Index: 6374855 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.5222. Min Act: -0.1700
Data Index: 1623008 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.4909. Min Act: -0.1700
Data Index: 4272511 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.4909. Min Act: -0.1700
Data Index: 7040681 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.4284. Min Act: -0.1700
Data Index: 5697505 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.3972. Min Act: -0.1700
Data Index: 3527369 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.3659. Min Act: -0.1700
Data Index: 5948030 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.3347. Min Act: -0.1700
Data Index: 6077521 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.3034. Min Act: -0.1700
Data Index: 5803190 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.3034. Min Act: -0.1700
Data Index: 2980360 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8972. Min Range: -6.8972
Max Act: 6.3034. Min Act: -0.1700
Data Index: 6874234 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19