Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.6496. Min Act: -0.1700
Data Index: 4030156 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.4617. Min Act: -0.1700
Data Index: 1869780 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.4617. Min Act: -0.1700
Data Index: 4809761 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.4461. Min Act: -0.1700
Data Index: 4809767 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3990. Min Act: -0.1700
Data Index: 1362728 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3990. Min Act: -0.1700
Data Index: 6672300 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3834. Min Act: -0.1700
Data Index: 2731315 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3990. Min Act: -0.1700
Data Index: 876538 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3834. Min Act: -0.1700
Data Index: 8024542 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3834. Min Act: -0.1700
Data Index: 6672299 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3834. Min Act: -0.1700
Data Index: 2930750 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3677. Min Act: -0.1700
Data Index: 4063543 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3520. Min Act: -0.1700
Data Index: 5226015 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3677. Min Act: -0.1700
Data Index: 2225958 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3520. Min Act: -0.1700
Data Index: 2185342 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3520. Min Act: -0.1700
Data Index: 8778709 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3520. Min Act: -0.1700
Data Index: 7609034 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3520. Min Act: -0.1700
Data Index: 7309823 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3206. Min Act: -0.1700
Data Index: 5826157 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6496. Min Range: -3.6496
Max Act: 3.3206. Min Act: -0.1700
Data Index: 628393 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19