Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5917. Min Range: -7.5917
Max Act: 7.5917. Min Act: -0.1700
Data Index: 7324409 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5917. Min Range: -7.5917
Max Act: 7.3105. Min Act: -0.1700
Data Index: 8275277 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5917. Min Range: -7.5917
Max Act: 7.2167. Min Act: -0.1700
Data Index: 657164 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5917. Min Range: -7.5917
Max Act: 7.0292. Min Act: -0.1700
Data Index: 6648525 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5917. Min Range: -7.5917
Max Act: 7.0605. Min Act: -0.1700
Data Index: 7505726 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.9355. Min Act: -0.1700
Data Index: 4410257 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.7480. Min Act: -0.1700
Data Index: 75905 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.6542. Min Act: -0.1700
Data Index: 2346042 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.6230. Min Act: -0.1700
Data Index: 621703 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.6230. Min Act: -0.1700
Data Index: 3538052 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5605. Min Act: -0.1700
Data Index: 283375 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5917. Min Act: -0.1700
Data Index: 1976346 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5917. Min Act: -0.1700
Data Index: 2299346 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5917. Min Act: -0.1700
Data Index: 4722336 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5917. Min Act: -0.1700
Data Index: 3400701 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5605. Min Act: -0.1700
Data Index: 8141822 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5292. Min Act: -0.1700
Data Index: 1931344 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5605. Min Act: -0.1700
Data Index: 714835 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5292. Min Act: -0.1700
Data Index: 6060449 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5917. Min Range: -7.5917
Max Act: 6.5292. Min Act: -0.1700
Data Index: 16526 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19