Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.9277. Min Act: -0.1700
Data Index: 1100939 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.9277. Min Act: -0.1700
Data Index: 1013744 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.8965. Min Act: -0.1700
Data Index: 3463754 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.8340. Min Act: -0.1700
Data Index: 1226604 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.8340. Min Act: -0.1700
Data Index: 3119106 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.8340. Min Act: -0.1700
Data Index: 2904587 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.8027. Min Act: -0.1700
Data Index: 3368510 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7715. Min Act: -0.1700
Data Index: 7803654 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.8027. Min Act: -0.1700
Data Index: 3270045 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7715. Min Act: -0.1700
Data Index: 948750 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7715. Min Act: -0.1700
Data Index: 5214993 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7715. Min Act: -0.1700
Data Index: 6427647 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7715. Min Act: -0.1700
Data Index: 7399503 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7715. Min Act: -0.1700
Data Index: 2239814 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7402. Min Act: -0.1700
Data Index: 8229907 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7402. Min Act: -0.1700
Data Index: 6570377 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7402. Min Act: -0.1700
Data Index: 3589815 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7402. Min Act: -0.1700
Data Index: 1078538 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7402. Min Act: -0.1700
Data Index: 7074845 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9277. Min Range: -5.9277
Max Act: 5.7090. Min Act: -0.1700
Data Index: 290151 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19