Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.2247. Min Act: -0.1699
Data Index: 6814671 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.2247. Min Act: -0.1700
Data Index: 7033780 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.1934. Min Act: -0.1700
Data Index: 4931843 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.1309. Min Act: -0.1698
Data Index: 2341480 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.1309. Min Act: -0.1700
Data Index: 1818078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.1309. Min Act: -0.1700
Data Index: 1789264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.0997. Min Act: -0.1700
Data Index: 6881710 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.0997. Min Act: -0.1700
Data Index: 8720495 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.0684. Min Act: -0.1700
Data Index: 2856691 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.0372. Min Act: -0.1700
Data Index: 2508252 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.0372. Min Act: -0.1700
Data Index: 2356258 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2247. Min Range: -5.2247
Max Act: 5.0059. Min Act: -0.1700
Data Index: 2490530 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9747. Min Act: -0.1700
Data Index: 2799965 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9747. Min Act: -0.1700
Data Index: 4220467 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9434. Min Act: -0.1700
Data Index: 1774174 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9434. Min Act: -0.1700
Data Index: 3616206 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9434. Min Act: -0.1700
Data Index: 3660806 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9434. Min Act: -0.1700
Data Index: 6014852 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9434. Min Act: -0.1700
Data Index: 4314350 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2247. Min Range: -5.2247
Max Act: 4.9434. Min Act: -0.1700
Data Index: 2878025 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19