Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5239 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.6296. Min Act: -0.1700
Data Index: 4538688 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5974. Min Act: -0.1700
Data Index: 2566853 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5813. Min Act: -0.1700
Data Index: 6906407 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5813. Min Act: -0.1700
Data Index: 2760712 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5491. Min Act: -0.1700
Data Index: 4943502 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5652. Min Act: -0.1700
Data Index: 7557661 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5491. Min Act: -0.1700
Data Index: 8588106 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5491. Min Act: -0.1700
Data Index: 5080787 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5329. Min Act: -0.1700
Data Index: 4328374 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5491. Min Act: -0.1700
Data Index: 2566863 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5167. Min Act: -0.1700
Data Index: 1371254 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5167. Min Act: -0.1700
Data Index: 1849619 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5167. Min Act: -0.1700
Data Index: 6418331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5005. Min Act: -0.1700
Data Index: 864696 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.4843. Min Act: -0.1700
Data Index: 83707 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.5005. Min Act: -0.1700
Data Index: 2566846 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.4843. Min Act: -0.1700
Data Index: 5418765 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.4843. Min Act: -0.1700
Data Index: 5706783 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.4681. Min Act: -0.1700
Data Index: 1181223 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6296. Min Range: -2.6296
Max Act: 2.4681. Min Act: -0.1700
Data Index: 5289238 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19