Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.7381. Min Act: -0.1700
Data Index: 5598134 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.7381. Min Act: -0.1700
Data Index: 7437312 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.7068. Min Act: -0.1700
Data Index: 5256888 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6119570 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6443. Min Act: -0.1700
Data Index: 2140059 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6443. Min Act: -0.1700
Data Index: 4291778 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6443. Min Act: -0.1700
Data Index: 7269876 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6131. Min Act: -0.1700
Data Index: 4394143 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 2109002 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 7007393 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5193. Min Act: -0.1700
Data Index: 1952664 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5193. Min Act: -0.1700
Data Index: 2066237 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4881. Min Act: -0.1700
Data Index: 7463505 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4256. Min Act: -0.1700
Data Index: 4664412 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4568. Min Act: -0.1700
Data Index: 3058974 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4568. Min Act: -0.1700
Data Index: 7551321 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4568. Min Act: -0.1700
Data Index: 108432 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4256. Min Act: -0.1700
Data Index: 7088359 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4256. Min Act: -0.1700
Data Index: 1297342 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4256. Min Act: -0.1700
Data Index: 2874758 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19