Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.7760. Min Act: -0.1700
Data Index: 1061726 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.8073. Min Act: -0.1700
Data Index: 5658184 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.7448. Min Act: -0.1700
Data Index: 2450313 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.7135. Min Act: -0.1700
Data Index: 5654916 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.6510. Min Act: -0.1700
Data Index: 4550784 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.6198. Min Act: -0.1700
Data Index: 7313134 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.6510. Min Act: -0.1700
Data Index: 5972661 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5573. Min Act: -0.1700
Data Index: 6689936 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5885. Min Act: -0.1700
Data Index: 1607335 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5885. Min Act: -0.1700
Data Index: 6463226 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5573. Min Act: -0.1700
Data Index: 276064 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5573. Min Act: -0.1700
Data Index: 511536 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5573. Min Act: -0.1700
Data Index: 5027670 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5260. Min Act: -0.1700
Data Index: 1170554 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5260. Min Act: -0.1700
Data Index: 1890723 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.5260. Min Act: -0.1700
Data Index: 3394376 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4948. Min Act: -0.1700
Data Index: 1141845 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4948. Min Act: -0.1700
Data Index: 1555980 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4635. Min Act: -0.1700
Data Index: 4393216 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4635. Min Act: -0.1700
Data Index: 72610 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19