Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.8488. Min Act: -0.1700
Data Index: 4065205 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.7550. Min Act: -0.1700
Data Index: 6139188 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.6925. Min Act: -0.1700
Data Index: 7511375 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.6925. Min Act: -0.1700
Data Index: 8349642 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.6613. Min Act: -0.1700
Data Index: 7502069 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.6300. Min Act: -0.1700
Data Index: 355162 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.5675. Min Act: -0.1700
Data Index: 5553705 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.5363. Min Act: -0.1700
Data Index: 3595730 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.5363. Min Act: -0.1700
Data Index: 6839206 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.4738. Min Act: -0.1700
Data Index: 1130406 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.4425. Min Act: -0.1700
Data Index: 689071 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.4425. Min Act: -0.1700
Data Index: 5092483 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.4113. Min Act: -0.1700
Data Index: 2536739 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.3800. Min Act: -0.1700
Data Index: 1269193 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.3800. Min Act: -0.1700
Data Index: 2065710 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.3488. Min Act: -0.1700
Data Index: 4933303 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.3488. Min Act: -0.1700
Data Index: 6233748 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.3175. Min Act: -0.1700
Data Index: 7384545 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.2238. Min Act: -0.1700
Data Index: 3539819 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8488. Min Range: -6.8488
Max Act: 6.2550. Min Act: -0.1700
Data Index: 7296510 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19