Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1626 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.9228. Min Act: -0.1700
Data Index: 2629428 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.7041. Min Act: -0.1700
Data Index: 2055391 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.5791. Min Act: -0.1700
Data Index: 2768018 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.5791. Min Act: -0.1700
Data Index: 1195863 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.4853. Min Act: -0.1700
Data Index: 6842050 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.4541. Min Act: -0.1700
Data Index: 3023000 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.3291. Min Act: -0.1700
Data Index: 2721290 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.3603. Min Act: -0.1700
Data Index: 6115433 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.3291. Min Act: -0.1700
Data Index: 2194922 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.3291. Min Act: -0.1700
Data Index: 1450777 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.2978. Min Act: -0.1700
Data Index: 4367774 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.2666. Min Act: -0.1700
Data Index: 2039484 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.2353. Min Act: -0.1700
Data Index: 3876955 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.2353. Min Act: -0.1700
Data Index: 1519758 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.2040. Min Act: -0.1700
Data Index: 3461996 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.2040. Min Act: -0.1700
Data Index: 1875156 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.2040. Min Act: -0.1700
Data Index: 5179063 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.1728. Min Act: -0.1700
Data Index: 5741815 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.1728. Min Act: -0.1700
Data Index: 72927 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9228. Min Range: -4.9228
Max Act: 4.1728. Min Act: -0.1700
Data Index: 4386278 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19