Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0420. Min Range: -6.0420
Max Act: 6.0420. Min Act: -0.1700
Data Index: 8774640 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.8545. Min Act: -0.1700
Data Index: 3702656 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.8233. Min Act: -0.1700
Data Index: 190223 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.7920. Min Act: -0.1700
Data Index: 4612785 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.7608. Min Act: -0.1700
Data Index: 1863353 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.7608. Min Act: -0.1700
Data Index: 1910734 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.7295. Min Act: -0.1700
Data Index: 3676539 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.7295. Min Act: -0.1700
Data Index: 7515031 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6983. Min Act: -0.1700
Data Index: 5520268 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6983. Min Act: -0.1700
Data Index: 5673021 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6983. Min Act: -0.1700
Data Index: 8066888 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6358. Min Act: -0.1700
Data Index: 5908655 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6670. Min Act: -0.1700
Data Index: 3987329 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6670. Min Act: -0.1700
Data Index: 5054290 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6670. Min Act: -0.1700
Data Index: 2238169 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6670. Min Act: -0.1700
Data Index: 2447530 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6358. Min Act: -0.1700
Data Index: 2452155 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6045. Min Act: -0.1700
Data Index: 3557199 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6045. Min Act: -0.1700
Data Index: 5069110 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0420. Min Range: -6.0420
Max Act: 5.6045. Min Act: -0.1700
Data Index: 1754991 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19