Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5607 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0147. Min Range: -6.0147
Max Act: 6.0147. Min Act: -0.1700
Data Index: 75926 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.9522. Min Act: -0.1700
Data Index: 353441 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.9209. Min Act: -0.1700
Data Index: 7736022 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.8897. Min Act: -0.1700
Data Index: 992825 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.8897. Min Act: -0.1700
Data Index: 3129969 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.7959. Min Act: -0.1700
Data Index: 8354276 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.7959. Min Act: -0.1700
Data Index: 3751678 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.7334. Min Act: -0.1700
Data Index: 1537022 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.7022. Min Act: -0.1700
Data Index: 5842669 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6709. Min Act: -0.1700
Data Index: 1761865 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6709. Min Act: -0.1700
Data Index: 8153178 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6397. Min Act: -0.1700
Data Index: 3638284 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6397. Min Act: -0.1700
Data Index: 4187830 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6397. Min Act: -0.1700
Data Index: 6804149 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6084. Min Act: -0.1700
Data Index: 7433911 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6397. Min Act: -0.1700
Data Index: 6088611 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6084. Min Act: -0.1700
Data Index: 3895515 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6084. Min Act: -0.1700
Data Index: 1686480 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6084. Min Act: -0.1700
Data Index: 5377847 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0147. Min Range: -6.0147
Max Act: 5.6084. Min Act: -0.1700
Data Index: 8714398 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19