Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1248. Min Range: -7.1248
Max Act: 7.1248. Min Act: -0.1700
Data Index: 4315058 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1248. Min Range: -7.1248
Max Act: 7.0623. Min Act: -0.1700
Data Index: 3925344 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1248. Min Range: -7.1248
Max Act: 7.0623. Min Act: -0.1700
Data Index: 8103039 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.8748. Min Act: -0.1700
Data Index: 530437 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.8435. Min Act: -0.1700
Data Index: 8619451 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.8123. Min Act: -0.1700
Data Index: 2805379 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.7810. Min Act: -0.1700
Data Index: 4384067 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.7810. Min Act: -0.1700
Data Index: 6022666 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.7185. Min Act: -0.1700
Data Index: 510969 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.7498. Min Act: -0.1700
Data Index: 1829508 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.7185. Min Act: -0.1700
Data Index: 3153287 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.6873. Min Act: -0.1700
Data Index: 3726677 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.6560. Min Act: -0.1700
Data Index: 1472695 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.6873. Min Act: -0.1700
Data Index: 3790656 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.5935. Min Act: -0.1700
Data Index: 5456491 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.6248. Min Act: -0.1700
Data Index: 8029135 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.5935. Min Act: -0.1700
Data Index: 4464695 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.5623. Min Act: -0.1700
Data Index: 6989994 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.5310. Min Act: -0.1700
Data Index: 2684704 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1248. Min Range: -7.1248
Max Act: 6.5310. Min Act: -0.1700
Data Index: 4516059 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19