Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4481 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.8408. Min Act: -0.1700
Data Index: 8741218 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.5748. Min Act: -0.1700
Data Index: 8373716 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.5748. Min Act: -0.1700
Data Index: 4611830 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.5279. Min Act: -0.1700
Data Index: 5462104 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.5122. Min Act: -0.1700
Data Index: 5188356 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.4965. Min Act: -0.1700
Data Index: 7390460 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.4809. Min Act: -0.1700
Data Index: 5106400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.4652. Min Act: -0.1700
Data Index: 2954310 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.4495. Min Act: -0.1700
Data Index: 6957201 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.4495. Min Act: -0.1700
Data Index: 3032542 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.4182. Min Act: -0.1700
Data Index: 6832844 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.4182. Min Act: -0.1700
Data Index: 1151642 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3868. Min Act: -0.1700
Data Index: 7596872 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3868. Min Act: -0.1700
Data Index: 4746764 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3868. Min Act: -0.1700
Data Index: 6505076 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3555. Min Act: -0.1700
Data Index: 1364552 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3555. Min Act: -0.1700
Data Index: 3107891 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3241. Min Act: -0.1700
Data Index: 3371444 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3555. Min Act: -0.1700
Data Index: 7948839 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8408. Min Range: -3.8408
Max Act: 3.3398. Min Act: -0.1700
Data Index: 3960136 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19