Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.9556. Min Act: -0.1700
Data Index: 4733334 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.7993. Min Act: -0.1700
Data Index: 2264304 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.6431. Min Act: -0.1700
Data Index: 4323712 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.6118. Min Act: -0.1700
Data Index: 2128086 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.5806. Min Act: -0.1700
Data Index: 5597003 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.5806. Min Act: -0.1700
Data Index: 4977458 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.4868. Min Act: -0.1700
Data Index: 2268351 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.4556. Min Act: -0.1700
Data Index: 5108441 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.4243. Min Act: -0.1700
Data Index: 651156 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.4243. Min Act: -0.1700
Data Index: 92950 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.3931. Min Act: -0.1700
Data Index: 5286714 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.3618. Min Act: -0.1700
Data Index: 1902684 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.3618. Min Act: -0.1700
Data Index: 6147546 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.3306. Min Act: -0.1700
Data Index: 3766948 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.2993. Min Act: -0.1700
Data Index: 7402050 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.2993. Min Act: -0.1700
Data Index: 5615827 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.2993. Min Act: -0.1700
Data Index: 2873229 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.2681. Min Act: -0.1700
Data Index: 5857079 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3983325 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9556. Min Range: -5.9556
Max Act: 5.2993. Min Act: -0.1700
Data Index: 4233923 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19