Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 4817998 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.3167. Min Act: -0.1700
Data Index: 195161 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 7202915 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 8699622 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2542. Min Act: -0.1700
Data Index: 1404548 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2542. Min Act: -0.1700
Data Index: 5504166 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2542. Min Act: -0.1700
Data Index: 3108641 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2229. Min Act: -0.1700
Data Index: 4459932 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2229. Min Act: -0.1700
Data Index: 5362636 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2229. Min Act: -0.1700
Data Index: 2917016 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2229. Min Act: -0.1700
Data Index: 5372485 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1917. Min Act: -0.1700
Data Index: 6902311 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2229. Min Act: -0.1700
Data Index: 5959773 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.2229. Min Act: -0.1700
Data Index: 7330188 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1604. Min Act: -0.1700
Data Index: 3254389 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1604. Min Act: -0.1700
Data Index: 3403197 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1604. Min Act: -0.1700
Data Index: 8383403 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1604. Min Act: -0.1700
Data Index: 8367087 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1604. Min Act: -0.1700
Data Index: 3077896 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3167. Min Range: -4.3167
Max Act: 4.1292. Min Act: -0.1700
Data Index: 3576238 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19