Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5373. Min Range: -5.5373
Max Act: 5.5373. Min Act: -0.1700
Data Index: 8143782 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5373. Min Range: -5.5373
Max Act: 5.0686. Min Act: -0.1700
Data Index: 636132 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5373. Min Range: -5.5373
Max Act: 5.0373. Min Act: -0.1700
Data Index: 7674021 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5373. Min Range: -5.5373
Max Act: 5.0061. Min Act: -0.1700
Data Index: 8164497 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.9436. Min Act: -0.1700
Data Index: 5822023 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.8811. Min Act: -0.1700
Data Index: 5384010 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2567872 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.9123. Min Act: -0.1700
Data Index: 5187531 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.8811. Min Act: -0.1700
Data Index: 4051082 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.8186. Min Act: -0.1700
Data Index: 5104417 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7873. Min Act: -0.1700
Data Index: 6550381 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7873. Min Act: -0.1700
Data Index: 5104407 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7873. Min Act: -0.1700
Data Index: 1435 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7873. Min Act: -0.1700
Data Index: 883757 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7248. Min Act: -0.1700
Data Index: 1363491 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7248. Min Act: -0.1700
Data Index: 2044354 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7248. Min Act: -0.1700
Data Index: 4515742 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7248. Min Act: -0.1700
Data Index: 1052230 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7561. Min Act: -0.1700
Data Index: 5653073 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5373. Min Range: -5.5373
Max Act: 4.7248. Min Act: -0.1700
Data Index: 808139 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19