Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.9366. Min Act: -0.1700
Data Index: 8786134 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.9054. Min Act: -0.1700
Data Index: 3655112 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.8741. Min Act: -0.1696
Data Index: 2939370 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.8429. Min Act: -0.1700
Data Index: 1476962 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7804. Min Act: -0.1700
Data Index: 6535976 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7804. Min Act: -0.1700
Data Index: 8091509 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7804. Min Act: -0.1700
Data Index: 6962609 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7804. Min Act: -0.1700
Data Index: 5876007 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7804. Min Act: -0.1700
Data Index: 546258 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5135129 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7179. Min Act: -0.1700
Data Index: 8761241 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7491. Min Act: -0.1700
Data Index: 4530066 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7491. Min Act: -0.1700
Data Index: 8173705 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7179. Min Act: -0.1700
Data Index: 3444195 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7179. Min Act: -0.1700
Data Index: 5594335 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.7179. Min Act: -0.1700
Data Index: 3643580 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.6866. Min Act: -0.1700
Data Index: 2463605 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.6866. Min Act: -0.1700
Data Index: 2928920 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.6866. Min Act: -0.1700
Data Index: 4324282 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9366. Min Range: -5.9366
Max Act: 5.6866. Min Act: -0.1700
Data Index: 5005446 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19