Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5908 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.4442. Min Act: -0.1700
Data Index: 3785421 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.3817. Min Act: -0.1700
Data Index: 3482522 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.3817. Min Act: -0.1700
Data Index: 7210197 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.2879. Min Act: -0.1700
Data Index: 2156390 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.2567. Min Act: -0.1700
Data Index: 6210924 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.1629. Min Act: -0.1700
Data Index: 6326253 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.2254. Min Act: -0.1700
Data Index: 3015936 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.1629. Min Act: -0.1700
Data Index: 899750 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.1629. Min Act: -0.1700
Data Index: 2909842 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.0379. Min Act: -0.1700
Data Index: 7884554 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.0379. Min Act: -0.1700
Data Index: 3498856 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4442. Min Range: -7.4442
Max Act: 7.0067. Min Act: -0.1700
Data Index: 5012916 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.9754. Min Act: -0.1700
Data Index: 3333358 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.9754. Min Act: -0.1700
Data Index: 480503 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.9754. Min Act: -0.1700
Data Index: 7753192 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.9442. Min Act: -0.1700
Data Index: 4813838 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.8504. Min Act: -0.1700
Data Index: 2504182 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.8504. Min Act: -0.1700
Data Index: 4234638 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.8504. Min Act: -0.1700
Data Index: 768655 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4442. Min Range: -7.4442
Max Act: 6.8504. Min Act: -0.1700
Data Index: 5436398 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19