Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4799 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.6159. Min Act: -0.1700
Data Index: 4430529 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.4909. Min Act: -0.1700
Data Index: 5625915 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.3659. Min Act: -0.1700
Data Index: 4111354 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.2409. Min Act: -0.1700
Data Index: 8595788 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.2409. Min Act: -0.1700
Data Index: 5292612 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.2409. Min Act: -0.1700
Data Index: 6500177 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.1784. Min Act: -0.1700
Data Index: 7923266 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.1784. Min Act: -0.1700
Data Index: 8305354 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.1784. Min Act: -0.1700
Data Index: 4748134 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.0846. Min Act: -0.1700
Data Index: 7653363 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.0534. Min Act: -0.1700
Data Index: 467773 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.0221. Min Act: -0.1700
Data Index: 8006781 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.0221. Min Act: -0.1700
Data Index: 2985671 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6159. Min Range: -8.6159
Max Act: 7.9909. Min Act: -0.1700
Data Index: 4995305 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6159. Min Range: -8.6159
Max Act: 7.9909. Min Act: -0.1700
Data Index: 2918198 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6159. Min Range: -8.6159
Max Act: 8.0221. Min Act: -0.1700
Data Index: 5269686 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6159. Min Range: -8.6159
Max Act: 7.9909. Min Act: -0.1700
Data Index: 4058894 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6159. Min Range: -8.6159
Max Act: 7.9909. Min Act: -0.1700
Data Index: 7510493 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6159. Min Range: -8.6159
Max Act: 7.9909. Min Act: -0.1700
Data Index: 7660406 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6159. Min Range: -8.6159
Max Act: 7.9284. Min Act: -0.1700
Data Index: 7301745 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19