Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6376 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.8524. Min Act: -0.1700
Data Index: 4353519 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.6649. Min Act: -0.1700
Data Index: 7984909 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.5399. Min Act: -0.1700
Data Index: 2903057 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.5399. Min Act: -0.1700
Data Index: 617518 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.4774. Min Act: -0.1700
Data Index: 65394 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.4149. Min Act: -0.1700
Data Index: 3424970 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.4149. Min Act: -0.1700
Data Index: 2723331 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.3524. Min Act: -0.1700
Data Index: 7775765 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.4149. Min Act: -0.1700
Data Index: 6389789 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.3524. Min Act: -0.1700
Data Index: 6004267 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.3524. Min Act: -0.1700
Data Index: 7203548 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.2899. Min Act: -0.1700
Data Index: 5402343 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.2899. Min Act: -0.1700
Data Index: 617517 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.3524. Min Act: -0.1700
Data Index: 7855971 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.2274. Min Act: -0.1700
Data Index: 4270757 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.2274. Min Act: -0.1700
Data Index: 6131430 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.1649. Min Act: -0.1700
Data Index: 4324750 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.1024. Min Act: -0.1700
Data Index: 929846 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.1024. Min Act: -0.1700
Data Index: 3503589 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8524. Min Range: -9.8524
Max Act: 9.1024. Min Act: -0.1700
Data Index: 6699440 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19