Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4371 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.2421. Min Act: -0.1700
Data Index: 451807 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.1484. Min Act: -0.1700
Data Index: 7769161 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.1171. Min Act: -0.1700
Data Index: 149150 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.1171. Min Act: -0.1700
Data Index: 5770418 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.0546. Min Act: -0.1700
Data Index: 8127563 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.0233. Min Act: -0.1700
Data Index: 7493460 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.0546. Min Act: -0.1700
Data Index: 7090498 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2421. Min Range: -4.2421
Max Act: 4.0546. Min Act: -0.1700
Data Index: 451806 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 4477452 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 6280154 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 5770419 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 672416 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 3014888 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 2977573 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 5514870 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9921. Min Act: -0.1700
Data Index: 4692756 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9608. Min Act: -0.1700
Data Index: 6828051 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9608. Min Act: -0.1700
Data Index: 1242256 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9608. Min Act: -0.1700
Data Index: 1678132 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2421. Min Range: -4.2421
Max Act: 3.9296. Min Act: -0.1700
Data Index: 3687933 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19