Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.5426. Min Act: -0.1700
Data Index: 7999518 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.5113. Min Act: -0.1700
Data Index: 3235236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.5113. Min Act: -0.1700
Data Index: 8163330 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.5113. Min Act: -0.1700
Data Index: 8394103 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4800. Min Act: -0.1700
Data Index: 6573866 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4800. Min Act: -0.1700
Data Index: 859919 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4800. Min Act: -0.1700
Data Index: 4064056 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4800. Min Act: -0.1700
Data Index: 731441 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4487. Min Act: -0.1700
Data Index: 1347910 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4487. Min Act: -0.1700
Data Index: 5362448 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4487. Min Act: -0.1700
Data Index: 2645201 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4487. Min Act: -0.1700
Data Index: 3760898 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4173. Min Act: -0.1700
Data Index: 386155 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4173. Min Act: -0.1700
Data Index: 7996734 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4173. Min Act: -0.1700
Data Index: 1807869 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4173. Min Act: -0.1700
Data Index: 5778994 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4173. Min Act: -0.1700
Data Index: 6323342 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.4173. Min Act: -0.1700
Data Index: 1975409 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.3860. Min Act: -0.1700
Data Index: 5920352 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5426. Min Range: -3.5426
Max Act: 3.3703. Min Act: -0.1700
Data Index: 1375700 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19