Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.6639. Min Act: -0.1700
Data Index: 2415613 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.6639. Min Act: -0.1700
Data Index: 5743980 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.5701. Min Act: -0.1700
Data Index: 2190275 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.5389. Min Act: -0.1700
Data Index: 3017845 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.4764. Min Act: -0.1700
Data Index: 202600 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.4451. Min Act: -0.1700
Data Index: 5414646 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.4451. Min Act: -0.1700
Data Index: 5148416 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.3826. Min Act: -0.1700
Data Index: 7938612 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.3826. Min Act: -0.1700
Data Index: 2755412 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.3201. Min Act: -0.1700
Data Index: 4934411 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.3201. Min Act: -0.1700
Data Index: 6538745 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.2889. Min Act: -0.1700
Data Index: 371612 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.2264. Min Act: -0.1700
Data Index: 7628611 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.2264. Min Act: -0.1700
Data Index: 2726395 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.2264. Min Act: -0.1700
Data Index: 5866962 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.2576. Min Act: -0.1700
Data Index: 7715260 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.2264. Min Act: -0.1700
Data Index: 2058026 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.1951. Min Act: -0.1700
Data Index: 3391454 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.1326. Min Act: -0.1700
Data Index: 5254351 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6639. Min Range: -6.6639
Max Act: 6.1951. Min Act: -0.1700
Data Index: 3030137 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19