Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.6314. Min Act: -0.1700
Data Index: 1625614 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.5218. Min Act: -0.1700
Data Index: 8807943 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.5062. Min Act: -0.1700
Data Index: 2094959 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.5062. Min Act: -0.1700
Data Index: 4270432 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.4905. Min Act: -0.1700
Data Index: 1625611 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.4749. Min Act: -0.1700
Data Index: 7064606 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.4592. Min Act: -0.1700
Data Index: 8381858 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.4435. Min Act: -0.1700
Data Index: 326209 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.4279. Min Act: -0.1700
Data Index: 8235160 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.4279. Min Act: -0.1700
Data Index: 6784128 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.4122. Min Act: -0.1700
Data Index: 8671506 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3965. Min Act: -0.1700
Data Index: 7918799 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3808. Min Act: -0.1700
Data Index: 794706 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3808. Min Act: -0.1700
Data Index: 6676851 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3808. Min Act: -0.1700
Data Index: 1856161 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3808. Min Act: -0.1700
Data Index: 5435048 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3808. Min Act: -0.1700
Data Index: 4187370 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3494. Min Act: -0.1700
Data Index: 104710 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3494. Min Act: -0.1700
Data Index: 494849 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6314. Min Range: -3.6314
Max Act: 3.3338. Min Act: -0.1700
Data Index: 6024079 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19