Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.7938. Min Act: -0.1700
Data Index: 5249866 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.7313. Min Act: -0.1700
Data Index: 3911568 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.6063. Min Act: -0.1700
Data Index: 2716715 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.5751. Min Act: -0.1700
Data Index: 8579947 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.5751. Min Act: -0.1700
Data Index: 1766004 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.5126. Min Act: -0.1700
Data Index: 4412796 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.4813. Min Act: -0.1700
Data Index: 6963167 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.4813. Min Act: -0.1700
Data Index: 395022 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.4501. Min Act: -0.1700
Data Index: 3490410 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.4188. Min Act: -0.1700
Data Index: 4714526 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.4501. Min Act: -0.1700
Data Index: 7663460 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3876. Min Act: -0.1700
Data Index: 5342200 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3563. Min Act: -0.1700
Data Index: 3908 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3563. Min Act: -0.1700
Data Index: 7946366 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3563. Min Act: -0.1700
Data Index: 4977914 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3563. Min Act: -0.1700
Data Index: 3646224 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3251. Min Act: -0.1700
Data Index: 6549636 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3251. Min Act: -0.1700
Data Index: 8569658 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.2938. Min Act: -0.1700
Data Index: 470527 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7938. Min Range: -5.7938
Max Act: 5.3251. Min Act: -0.1700
Data Index: 6453739 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19