Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.5830. Min Act: -0.1700
Data Index: 7466468 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.5205. Min Act: -0.1700
Data Index: 5845883 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.3330. Min Act: -0.1700
Data Index: 1420521 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.3330. Min Act: -0.1700
Data Index: 2810671 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.1455. Min Act: -0.1700
Data Index: 5842224 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.0830. Min Act: -0.1700
Data Index: 5792948 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.0830. Min Act: -0.1700
Data Index: 5980642 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.0830. Min Act: -0.1700
Data Index: 5572151 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.0830. Min Act: -0.1700
Data Index: 5753290 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.0205. Min Act: -0.1700
Data Index: 2287175 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.0205. Min Act: -0.1700
Data Index: 6073628 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5830. Min Range: -9.5830
Max Act: 9.0205. Min Act: -0.1700
Data Index: 5572150 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.8955. Min Act: -0.1700
Data Index: 2423535 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.8955. Min Act: -0.1700
Data Index: 3716704 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.8955. Min Act: -0.1700
Data Index: 7186569 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.8955. Min Act: -0.1700
Data Index: 6370753 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.8955. Min Act: -0.1700
Data Index: 1979857 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.8955. Min Act: -0.1700
Data Index: 8605361 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.7705. Min Act: -0.1700
Data Index: 6628777 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5830. Min Range: -9.5830
Max Act: 8.8330. Min Act: -0.1700
Data Index: 7851637 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19