Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3276. Min Range: -10.3276
Max Act: 10.3276. Min Act: -0.1700
Data Index: 8201625 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3276. Min Range: -10.3276
Max Act: 10.3276. Min Act: -0.1699
Data Index: 8075506 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3276. Min Range: -10.3276
Max Act: 10.1401. Min Act: -0.1699
Data Index: 7530967 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3276. Min Range: -10.3276
Max Act: 10.0151. Min Act: -0.1700
Data Index: 5092131 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3276. Min Range: -10.3276
Max Act: 10.0151. Min Act: -0.1700
Data Index: 1482618 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3276. Min Range: -10.3276
Max Act: 10.0151. Min Act: -0.1700
Data Index: 1698501 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3276. Min Range: -10.3276
Max Act: 10.0151. Min Act: -0.1698
Data Index: 3012547 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.9526. Min Act: -0.1700
Data Index: 8487066 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.8901. Min Act: -0.1700
Data Index: 3961862 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.8276. Min Act: -0.1700
Data Index: 898711 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.8901. Min Act: -0.1687
Data Index: 6230617 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.8276. Min Act: -0.1700
Data Index: 8725496 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.7651. Min Act: -0.1700
Data Index: 5090141 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.8901. Min Act: -0.1698
Data Index: 5755609 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.7651. Min Act: -0.1699
Data Index: 3936323 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.7651. Min Act: -0.1697
Data Index: 4741717 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.7651. Min Act: -0.1699
Data Index: 4148786 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.7651. Min Act: -0.1699
Data Index: 7400905 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.7026. Min Act: -0.1700
Data Index: 1526173 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3276. Min Range: -10.3276
Max Act: 9.7026. Min Act: -0.1700
Data Index: 7707686 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19