Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5070. Min Range: -8.5070
Max Act: 8.5070. Min Act: -0.1700
Data Index: 8007298 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5070. Min Range: -8.5070
Max Act: 8.3820. Min Act: -0.1700
Data Index: 5956568 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5070. Min Range: -8.5070
Max Act: 8.1945. Min Act: -0.1700
Data Index: 6146893 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5070. Min Range: -8.5070
Max Act: 8.1632. Min Act: -0.1700
Data Index: 2155881 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5070. Min Range: -8.5070
Max Act: 8.0695. Min Act: -0.1700
Data Index: 4586896 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5070. Min Range: -8.5070
Max Act: 8.0695. Min Act: -0.1700
Data Index: 648286 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5070. Min Range: -8.5070
Max Act: 8.0695. Min Act: -0.1700
Data Index: 3573183 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.9757. Min Act: -0.1700
Data Index: 593795 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.9757. Min Act: -0.1700
Data Index: 8793707 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.9132. Min Act: -0.1700
Data Index: 7731736 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.8195. Min Act: -0.1700
Data Index: 4879449 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.8507. Min Act: -0.1700
Data Index: 1332237 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.7882. Min Act: -0.1700
Data Index: 2957590 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.7882. Min Act: -0.1700
Data Index: 7354188 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.7570. Min Act: -0.1700
Data Index: 2155880 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.7257. Min Act: -0.1700
Data Index: 3041465 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.7257. Min Act: -0.1700
Data Index: 1272721 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.6632. Min Act: -0.1700
Data Index: 1275347 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.6007. Min Act: -0.1700
Data Index: 7813663 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5070. Min Range: -8.5070
Max Act: 7.6320. Min Act: -0.1700
Data Index: 2325875 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19