Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 531 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0408. Min Range: -6.0408
Max Act: 6.0408. Min Act: -0.1700
Data Index: 7921414 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.9471. Min Act: -0.1700
Data Index: 892864 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.9158. Min Act: -0.1700
Data Index: 4630137 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.8846. Min Act: -0.1700
Data Index: 1029153 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.8221. Min Act: -0.1700
Data Index: 3183569 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.8221. Min Act: -0.1700
Data Index: 5978260 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7908. Min Act: -0.1700
Data Index: 5651496 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 5994100 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 7820755 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 8030824 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 6767094 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 8596944 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6971. Min Act: -0.1700
Data Index: 2856034 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.7283. Min Act: -0.1700
Data Index: 4358886 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6971. Min Act: -0.1700
Data Index: 6602980 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6658. Min Act: -0.1700
Data Index: 1818219 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6658. Min Act: -0.1700
Data Index: 7976195 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6658. Min Act: -0.1700
Data Index: 4625174 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6346. Min Act: -0.1700
Data Index: 6498644 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0408. Min Range: -6.0408
Max Act: 5.6346. Min Act: -0.1700
Data Index: 1728735 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19