Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5742 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.3031. Min Act: -0.1700
Data Index: 5556363 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.2094. Min Act: -0.1700
Data Index: 2199802 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.2094. Min Act: -0.1700
Data Index: 486409 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0219. Min Act: -0.1700
Data Index: 2473792 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0219. Min Act: -0.1700
Data Index: 4253639 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.9906. Min Act: -0.1700
Data Index: 4962272 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.9594. Min Act: -0.1700
Data Index: 8723429 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.9281. Min Act: -0.1700
Data Index: 2914480 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 8706208 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 2473787 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 1334863 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 4137415 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8656. Min Act: -0.1700
Data Index: 5206975 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8656. Min Act: -0.1700
Data Index: 7191623 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8656. Min Act: -0.1700
Data Index: 4423855 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8656. Min Act: -0.1700
Data Index: 2649123 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8344. Min Act: -0.1700
Data Index: 6981123 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8031. Min Act: -0.1700
Data Index: 6698264 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8344. Min Act: -0.1700
Data Index: 3505795 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8031. Min Act: -0.1700
Data Index: 4601054 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19