Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5382 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.2670. Min Act: -0.1700
Data Index: 567001 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.2670. Min Act: -0.1700
Data Index: 131763 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.2357. Min Act: -0.1700
Data Index: 4865699 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.2357. Min Act: -0.1700
Data Index: 5850362 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.1420. Min Act: -0.1700
Data Index: 8142300 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.1420. Min Act: -0.1700
Data Index: 5629217 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.0482. Min Act: -0.1700
Data Index: 2028310 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9857. Min Act: -0.1700
Data Index: 5850361 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.0170. Min Act: -0.1700
Data Index: 4973667 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.0482. Min Act: -0.1700
Data Index: 174451 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2670. Min Range: -7.2670
Max Act: 7.0170. Min Act: -0.1700
Data Index: 4628139 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9545. Min Act: -0.1700
Data Index: 7511152 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9857. Min Act: -0.1700
Data Index: 3511534 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9857. Min Act: -0.1700
Data Index: 6248345 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9857. Min Act: -0.1700
Data Index: 556950 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9545. Min Act: -0.1700
Data Index: 273767 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9857. Min Act: -0.1700
Data Index: 5476072 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9545. Min Act: -0.1700
Data Index: 8147475 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9545. Min Act: -0.1700
Data Index: 3697197 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2670. Min Range: -7.2670
Max Act: 6.9232. Min Act: -0.1700
Data Index: 1991680 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19