Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.9214. Min Act: -0.1700
Data Index: 318790 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.9526. Min Act: -0.1700
Data Index: 1095738 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.8276. Min Act: -0.1700
Data Index: 1346416 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.7339. Min Act: -0.1700
Data Index: 8438411 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.7339. Min Act: -0.1700
Data Index: 4948291 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.7651. Min Act: -0.1700
Data Index: 8092816 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.7026. Min Act: -0.1700
Data Index: 2488150 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.7651. Min Act: -0.1700
Data Index: 8025986 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.7026. Min Act: -0.1700
Data Index: 3807149 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.7339. Min Act: -0.1700
Data Index: 6753529 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.6714. Min Act: -0.1700
Data Index: 6977629 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.6401. Min Act: -0.1700
Data Index: 4488013 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.6089. Min Act: -0.1700
Data Index: 7128659 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.6089. Min Act: -0.1700
Data Index: 4327805 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.5776. Min Act: -0.1700
Data Index: 1677374 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.5776. Min Act: -0.1700
Data Index: 3522717 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.5776. Min Act: -0.1700
Data Index: 4211476 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.5151. Min Act: -0.1700
Data Index: 1171537 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.5464. Min Act: -0.1700
Data Index: 859685 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9526. Min Range: -5.9526
Max Act: 5.5464. Min Act: -0.1700
Data Index: 5990247 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19