Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4592 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.9211. Min Act: -0.1700
Data Index: 6595332 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.8585. Min Act: -0.1700
Data Index: 4577638 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.8273. Min Act: -0.1700
Data Index: 1161259 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7960. Min Act: -0.1700
Data Index: 666444 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7960. Min Act: -0.1700
Data Index: 4408393 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7960. Min Act: -0.1700
Data Index: 6045697 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7647. Min Act: -0.1700
Data Index: 6150246 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7647. Min Act: -0.1700
Data Index: 7086536 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7647. Min Act: -0.1700
Data Index: 5563947 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7647. Min Act: -0.1700
Data Index: 7111345 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7647. Min Act: -0.1700
Data Index: 7406028 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7647. Min Act: -0.1700
Data Index: 4652404 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7334. Min Act: -0.1700
Data Index: 4932457 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7334. Min Act: -0.1700
Data Index: 6800396 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7022. Min Act: -0.1700
Data Index: 3819062 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7334. Min Act: -0.1700
Data Index: 7232688 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7334. Min Act: -0.1698
Data Index: 5269157 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7022. Min Act: -0.1700
Data Index: 6157224 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7022. Min Act: -0.1700
Data Index: 6045698 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9211. Min Range: -3.9211
Max Act: 3.7022. Min Act: -0.1700
Data Index: 3125086 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19