Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0640. Min Range: -6.0640
Max Act: 6.0640. Min Act: -0.1700
Data Index: 2709746 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.8765. Min Act: -0.1700
Data Index: 8369844 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.8140. Min Act: -0.1700
Data Index: 2137336 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.8453. Min Act: -0.1700
Data Index: 4307381 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.8140. Min Act: -0.1700
Data Index: 2758646 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7828. Min Act: -0.1700
Data Index: 6951714 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7828. Min Act: -0.1700
Data Index: 6862951 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7515. Min Act: -0.1700
Data Index: 7015553 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7828. Min Act: -0.1700
Data Index: 5261724 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7515. Min Act: -0.1700
Data Index: 620873 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7515. Min Act: -0.1700
Data Index: 4506925 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7515. Min Act: -0.1700
Data Index: 2386306 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.6890. Min Act: -0.1700
Data Index: 7660204 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7203. Min Act: -0.1700
Data Index: 6636541 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.7203. Min Act: -0.1700
Data Index: 1424044 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.6890. Min Act: -0.1700
Data Index: 2591296 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.6890. Min Act: -0.1700
Data Index: 504101 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.6578. Min Act: -0.1700
Data Index: 143708 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.6578. Min Act: -0.1700
Data Index: 1894433 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0640. Min Range: -6.0640
Max Act: 5.6578. Min Act: -0.1700
Data Index: 633425 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19