Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.5777. Min Act: -0.1700
Data Index: 4108649 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.5152. Min Act: -0.1700
Data Index: 5515748 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.3277. Min Act: -0.1700
Data Index: 1096653 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.2027. Min Act: -0.1700
Data Index: 7895653 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.2027. Min Act: -0.1700
Data Index: 439499 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.1402. Min Act: -0.1700
Data Index: 1561088 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.0777. Min Act: -0.1700
Data Index: 6143347 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.0152. Min Act: -0.1700
Data Index: 3261115 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5777. Min Range: -10.5777
Max Act: 10.0152. Min Act: -0.1700
Data Index: 6823253 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.9527. Min Act: -0.1700
Data Index: 5595230 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.9527. Min Act: -0.1700
Data Index: 99451 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.9527. Min Act: -0.1700
Data Index: 7927253 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.9527. Min Act: -0.1700
Data Index: 2001237 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.9527. Min Act: -0.1700
Data Index: 4179929 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.8902. Min Act: -0.1700
Data Index: 3407892 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.8277. Min Act: -0.1700
Data Index: 2625413 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.8902. Min Act: -0.1700
Data Index: 7544783 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.7652. Min Act: -0.1700
Data Index: 8341996 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.7652. Min Act: -0.1700
Data Index: 5182233 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5777. Min Range: -10.5777
Max Act: 9.7652. Min Act: -0.1700
Data Index: 7367711 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19