Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2366. Min Range: -6.2366
Max Act: 6.2366. Min Act: -0.1700
Data Index: 6009748 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2366. Min Range: -6.2366
Max Act: 6.0178. Min Act: -0.1700
Data Index: 2658684 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.8303. Min Act: -0.1700
Data Index: 3340006 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7678. Min Act: -0.1700
Data Index: 5404832 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7678. Min Act: -0.1700
Data Index: 8045939 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7366. Min Act: -0.1700
Data Index: 7025862 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7053. Min Act: -0.1700
Data Index: 7046968 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.7053. Min Act: -0.1700
Data Index: 7070587 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6741. Min Act: -0.1700
Data Index: 7936335 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6741. Min Act: -0.1700
Data Index: 2726097 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6116. Min Act: -0.1700
Data Index: 3675496 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6428. Min Act: -0.1700
Data Index: 1867197 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6428. Min Act: -0.1700
Data Index: 8058290 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6428. Min Act: -0.1700
Data Index: 4361715 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6116. Min Act: -0.1700
Data Index: 5250500 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6116. Min Act: -0.1700
Data Index: 2072591 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.6116. Min Act: -0.1700
Data Index: 8788927 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.5803. Min Act: -0.1700
Data Index: 4515471 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.5803. Min Act: -0.1700
Data Index: 896048 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2366. Min Range: -6.2366
Max Act: 5.5491. Min Act: -0.1700
Data Index: 183565 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19