Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.4442. Min Act: -0.1700
Data Index: 1293709 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.4130. Min Act: -0.1700
Data Index: 1322681 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3817. Min Act: -0.1700
Data Index: 8626233 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3817. Min Act: -0.1700
Data Index: 3515865 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3817. Min Act: -0.1700
Data Index: 3797364 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3505. Min Act: -0.1696
Data Index: 4223439 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3817. Min Act: -0.1700
Data Index: 7084980 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3192. Min Act: -0.1700
Data Index: 2414857 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3192. Min Act: -0.1700
Data Index: 3621870 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3192. Min Act: -0.1700
Data Index: 2881287 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3192. Min Act: -0.1700
Data Index: 6234237 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2880. Min Act: -0.1700
Data Index: 4703090 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2880. Min Act: -0.1700
Data Index: 4761892 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2880. Min Act: -0.1699
Data Index: 142538 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2567. Min Act: -0.1700
Data Index: 7007469 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2880. Min Act: -0.1700
Data Index: 4451274 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2880. Min Act: -0.1700
Data Index: 5765658 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2880. Min Act: -0.1700
Data Index: 5118736 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.2880. Min Act: -0.1700
Data Index: 4998271 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4442. Min Range: -5.4442
Max Act: 5.3192. Min Act: -0.1699
Data Index: 4903917 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19