Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5364 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.9368. Min Act: -0.1700
Data Index: 1396513 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.4368. Min Act: -0.1700
Data Index: 1463257 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.4368. Min Act: -0.1700
Data Index: 591423 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.4056. Min Act: -0.1700
Data Index: 1118071 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.3118. Min Act: -0.1700
Data Index: 1566774 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.2806. Min Act: -0.1700
Data Index: 1967052 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1868. Min Act: -0.1700
Data Index: 3644430 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1556. Min Act: -0.1700
Data Index: 1800087 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1868. Min Act: -0.1700
Data Index: 6950046 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1556. Min Act: -0.1700
Data Index: 324513 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 756073 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 6821865 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 3668274 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 8717371 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 8622543 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.0931. Min Act: -0.1700
Data Index: 7238402 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 1888071 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.0931. Min Act: -0.1700
Data Index: 28784 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.0931. Min Act: -0.1700
Data Index: 5442343 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9368. Min Range: -5.9368
Max Act: 5.0931. Min Act: -0.1700
Data Index: 3110986 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19