Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.9914. Min Act: -0.1700
Data Index: 506911 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0227. Min Range: -6.0227
Max Act: 6.0227. Min Act: -0.1700
Data Index: 1375099 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.9289. Min Act: -0.1700
Data Index: 7670764 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.9602. Min Act: -0.1700
Data Index: 1261853 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.9602. Min Act: -0.1700
Data Index: 6838130 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.8664. Min Act: -0.1700
Data Index: 494328 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.8664. Min Act: -0.1700
Data Index: 8359763 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.8664. Min Act: -0.1700
Data Index: 5189167 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.8352. Min Act: -0.1700
Data Index: 1521753 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.8039. Min Act: -0.1700
Data Index: 1962545 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.8039. Min Act: -0.1700
Data Index: 2462078 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.7414. Min Act: -0.1700
Data Index: 7912297 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.7414. Min Act: -0.1700
Data Index: 77412 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.7102. Min Act: -0.1700
Data Index: 6211640 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.7102. Min Act: -0.1700
Data Index: 7521318 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.7102. Min Act: -0.1700
Data Index: 8621551 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.6789. Min Act: -0.1700
Data Index: 6529807 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.6477. Min Act: -0.1700
Data Index: 8196408 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.6477. Min Act: -0.1700
Data Index: 4410416 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0227. Min Range: -6.0227
Max Act: 5.6477. Min Act: -0.1700
Data Index: 8088739 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19