Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0340. Min Range: -5.0340
Max Act: 5.0340. Min Act: -0.1700
Data Index: 3887817 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0340. Min Range: -5.0340
Max Act: 5.0028. Min Act: -0.1700
Data Index: 5314759 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.9403. Min Act: -0.1700
Data Index: 1318274 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.9403. Min Act: -0.1700
Data Index: 8415779 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.9090. Min Act: -0.1700
Data Index: 7002582 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.9403. Min Act: -0.1700
Data Index: 2710964 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.9090. Min Act: -0.1700
Data Index: 355724 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.9403. Min Act: -0.1700
Data Index: 58790 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8778. Min Act: -0.1700
Data Index: 4258138 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8778. Min Act: -0.1700
Data Index: 4358364 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8778. Min Act: -0.1700
Data Index: 7960135 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8778. Min Act: -0.1700
Data Index: 7803211 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8778. Min Act: -0.1700
Data Index: 7399491 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8153. Min Act: -0.1700
Data Index: 5360108 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8465. Min Act: -0.1700
Data Index: 5826976 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8153. Min Act: -0.1700
Data Index: 1675866 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8153. Min Act: -0.1700
Data Index: 3240448 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8465. Min Act: -0.1700
Data Index: 1150036 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8153. Min Act: -0.1700
Data Index: 931062 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0340. Min Range: -5.0340
Max Act: 4.8153. Min Act: -0.1700
Data Index: 7241024 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19