Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4387 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.7903. Min Act: -0.1700
Data Index: 895602 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6340. Min Act: -0.1700
Data Index: 5511429 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6653. Min Act: -0.1700
Data Index: 5377057 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6340. Min Act: -0.1700
Data Index: 1986367 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6340. Min Act: -0.1700
Data Index: 4350046 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6340. Min Act: -0.1700
Data Index: 2195167 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6028. Min Act: -0.1700
Data Index: 2499600 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6028. Min Act: -0.1700
Data Index: 6450027 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.6028. Min Act: -0.1700
Data Index: 6602069 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.5715. Min Act: -0.1700
Data Index: 4509113 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.5403. Min Act: -0.1700
Data Index: 3203 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.5090. Min Act: -0.1700
Data Index: 4978576 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.4778. Min Act: -0.1700
Data Index: 4401784 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.4465. Min Act: -0.1700
Data Index: 7137878 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.4465. Min Act: -0.1700
Data Index: 5944411 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.4153. Min Act: -0.1700
Data Index: 5529535 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.4153. Min Act: -0.1700
Data Index: 3901960 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.3840. Min Act: -0.1700
Data Index: 8194014 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.3528. Min Act: -0.1700
Data Index: 529351 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7903. Min Range: -7.7903
Max Act: 7.3528. Min Act: -0.1700
Data Index: 4781510 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19