Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3365 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4170. Min Range: -5.4170
Max Act: 5.4170. Min Act: -0.1700
Data Index: 5584733 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4170. Min Range: -5.4170
Max Act: 5.0733. Min Act: -0.1700
Data Index: 1932056 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4170. Min Range: -5.4170
Max Act: 5.0420. Min Act: -0.1700
Data Index: 2440178 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4170. Min Range: -5.4170
Max Act: 5.0108. Min Act: -0.1700
Data Index: 393693 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4170. Min Range: -5.4170
Max Act: 5.0108. Min Act: -0.1700
Data Index: 5584709 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.9795. Min Act: -0.1700
Data Index: 954559 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.8545. Min Act: -0.1700
Data Index: 1932061 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.8233. Min Act: -0.1700
Data Index: 8684067 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.8545. Min Act: -0.1700
Data Index: 5584686 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7920. Min Act: -0.1700
Data Index: 1932063 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7920. Min Act: -0.1700
Data Index: 6204752 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7920. Min Act: -0.1700
Data Index: 7046045 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7920. Min Act: -0.1700
Data Index: 7920377 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7920. Min Act: -0.1700
Data Index: 7992966 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7608. Min Act: -0.1700
Data Index: 5676440 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7295. Min Act: -0.1700
Data Index: 393679 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7295. Min Act: -0.1700
Data Index: 5588954 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7295. Min Act: -0.1700
Data Index: 341064 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.7295. Min Act: -0.1700
Data Index: 341035 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4170. Min Range: -5.4170
Max Act: 4.6982. Min Act: -0.1700
Data Index: 5588965 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19