Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.1411. Min Act: -0.1700
Data Index: 151480 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.1411. Min Act: -0.1700
Data Index: 6588400 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.1411. Min Act: -0.1700
Data Index: 4612260 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.1098. Min Act: -0.1700
Data Index: 601157 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0786. Min Act: -0.1700
Data Index: 571664 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0786. Min Act: -0.1700
Data Index: 3427799 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.1098. Min Act: -0.1700
Data Index: 21626 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0786. Min Act: -0.1700
Data Index: 3837148 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0786. Min Act: -0.1700
Data Index: 138676 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0786. Min Act: -0.1700
Data Index: 5516246 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0473. Min Act: -0.1700
Data Index: 5490355 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0473. Min Act: -0.1700
Data Index: 2395748 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0473. Min Act: -0.1700
Data Index: 6135904 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0473. Min Act: -0.1700
Data Index: 2065675 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0473. Min Act: -0.1700
Data Index: 3531324 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0473. Min Act: -0.1700
Data Index: 8803648 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0160. Min Act: -0.1700
Data Index: 1033285 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0160. Min Act: -0.1700
Data Index: 4344606 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0160. Min Act: -0.1700
Data Index: 6504192 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0160. Min Act: -0.1700
Data Index: 888259 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19