Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.9674. Min Act: -0.1700
Data Index: 6499163 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.9674. Min Act: -0.1700
Data Index: 7006718 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.7799. Min Act: -0.1700
Data Index: 2508400 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.6549. Min Act: -0.1700
Data Index: 1208766 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5612. Min Act: -0.1700
Data Index: 1404941 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.5612. Min Act: -0.1700
Data Index: 8822069 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.4987. Min Act: -0.1700
Data Index: 6201467 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.4674. Min Act: -0.1700
Data Index: 2061637 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.4674. Min Act: -0.1700
Data Index: 7022526 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.4362. Min Act: -0.1700
Data Index: 3125877 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.4674. Min Act: -0.1700
Data Index: 729351 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3737. Min Act: -0.1700
Data Index: 5366255 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3737. Min Act: -0.1700
Data Index: 3220304 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3737. Min Act: -0.1700
Data Index: 702662 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3424. Min Act: -0.1700
Data Index: 7239895 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3112. Min Act: -0.1700
Data Index: 1527578 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3424. Min Act: -0.1700
Data Index: 596931 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3112. Min Act: -0.1700
Data Index: 4240860 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3112. Min Act: -0.1700
Data Index: 6007779 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9674. Min Range: -5.9674
Max Act: 5.3424. Min Act: -0.1700
Data Index: 383089 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19