Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3317 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.4898. Min Act: -0.1700
Data Index: 8816828 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.4898. Min Act: -0.1700
Data Index: 4623321 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.4586. Min Act: -0.1700
Data Index: 4623314 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.4586. Min Act: -0.1700
Data Index: 7476077 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3961. Min Act: -0.1700
Data Index: 1688121 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3961. Min Act: -0.1700
Data Index: 2665132 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3648. Min Act: -0.1700
Data Index: 4623323 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3648. Min Act: -0.1700
Data Index: 5089948 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3648. Min Act: -0.1700
Data Index: 8295443 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3336. Min Act: -0.1700
Data Index: 3597474 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3336. Min Act: -0.1700
Data Index: 1287299 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4183221 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 2328044 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 6103728 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4623307 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 3361178 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4623316 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.2711. Min Act: -0.1700
Data Index: 4623301 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.2711. Min Act: -0.1700
Data Index: 6364441 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.2711. Min Act: -0.1700
Data Index: 5286390 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19