Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.5543. Min Act: -0.1700
Data Index: 2816107 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.3668. Min Act: -0.1700
Data Index: 1782786 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.3355. Min Act: -0.1700
Data Index: 7216576 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.3355. Min Act: -0.1700
Data Index: 4048467 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.3043. Min Act: -0.1700
Data Index: 650765 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2105. Min Act: -0.1700
Data Index: 4743131 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0855. Min Act: -0.1700
Data Index: 8424979 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1168. Min Act: -0.1700
Data Index: 8597831 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1168. Min Act: -0.1700
Data Index: 2744045 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1168. Min Act: -0.1700
Data Index: 352778 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1168. Min Act: -0.1700
Data Index: 1047602 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1168. Min Act: -0.1700
Data Index: 42522 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0543. Min Act: -0.1700
Data Index: 5093082 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0855. Min Act: -0.1700
Data Index: 3575094 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0855. Min Act: -0.1700
Data Index: 3534909 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0855. Min Act: -0.1700
Data Index: 3610079 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0855. Min Act: -0.1700
Data Index: 1283097 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0543. Min Act: -0.1700
Data Index: 2121017 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5543. Min Range: -6.5543
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3829673 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.0230. Min Act: -0.1700
Data Index: 160342 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19