Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.7790. Min Act: -0.1700
Data Index: 5470759 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.7165. Min Act: -0.1700
Data Index: 4878082 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.6540. Min Act: -0.1700
Data Index: 5730184 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.6227. Min Act: -0.1700
Data Index: 3429891 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5915. Min Act: -0.1700
Data Index: 1027374 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5602. Min Act: -0.1700
Data Index: 5228380 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5602. Min Act: -0.1700
Data Index: 3895100 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5290. Min Act: -0.1700
Data Index: 8150568 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6395200 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5290. Min Act: -0.1700
Data Index: 7011543 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5290. Min Act: -0.1700
Data Index: 8389059 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5290. Min Act: -0.1700
Data Index: 3122218 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.5290. Min Act: -0.1700
Data Index: 2300414 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4977. Min Act: -0.1700
Data Index: 564240 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4665. Min Act: -0.1700
Data Index: 2651566 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4977. Min Act: -0.1700
Data Index: 3231836 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4665. Min Act: -0.1700
Data Index: 4355484 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4977. Min Act: -0.1700
Data Index: 2181921 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4977. Min Act: -0.1700
Data Index: 4202481 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7790. Min Range: -4.7790
Max Act: 4.4977. Min Act: -0.1700
Data Index: 1868408 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19