Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3278. Min Range: -7.3278
Max Act: 7.3278. Min Act: -0.1700
Data Index: 7112940 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.9528. Min Act: -0.1700
Data Index: 1428003 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.9215. Min Act: -0.1700
Data Index: 5700051 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.8590. Min Act: -0.1700
Data Index: 2808325 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.8590. Min Act: -0.1700
Data Index: 6830925 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7965. Min Act: -0.1700
Data Index: 7655475 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.8278. Min Act: -0.1700
Data Index: 86613 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7340. Min Act: -0.1700
Data Index: 1559630 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 1320899 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7340. Min Act: -0.1700
Data Index: 1889652 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 7136793 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 6238519 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 5603019 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.6715. Min Act: -0.1700
Data Index: 2939509 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 1728322 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.6715. Min Act: -0.1700
Data Index: 3161383 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.6715. Min Act: -0.1700
Data Index: 459109 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.6715. Min Act: -0.1700
Data Index: 1067186 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.6403. Min Act: -0.1700
Data Index: 7851475 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3278. Min Range: -7.3278
Max Act: 6.6715. Min Act: -0.1700
Data Index: 3433168 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19