Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.8586. Min Act: -0.1700
Data Index: 7355317 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.7336. Min Act: -0.1700
Data Index: 6375469 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.7649. Min Act: -0.1700
Data Index: 4247312 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.7024. Min Act: -0.1700
Data Index: 8703394 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.6399. Min Act: -0.1700
Data Index: 608885 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.6711. Min Act: -0.1700
Data Index: 6484862 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.6086. Min Act: -0.1700
Data Index: 7128175 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.6086. Min Act: -0.1700
Data Index: 168542 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.5461. Min Act: -0.1700
Data Index: 2568686 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.5149. Min Act: -0.1700
Data Index: 2880284 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.5461. Min Act: -0.1700
Data Index: 3971220 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.5149. Min Act: -0.1700
Data Index: 6453819 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.5149. Min Act: -0.1700
Data Index: 1507697 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.4836. Min Act: -0.1700
Data Index: 2306874 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.4836. Min Act: -0.1700
Data Index: 6534104 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.4524. Min Act: -0.1700
Data Index: 1705792 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.4524. Min Act: -0.1700
Data Index: 5452028 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.4524. Min Act: -0.1700
Data Index: 2484721 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.4524. Min Act: -0.1700
Data Index: 1355134 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8586. Min Range: -6.8586
Max Act: 6.4524. Min Act: -0.1700
Data Index: 4343043 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19