Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0011. Min Range: -4.0011
Max Act: 4.0011. Min Act: -0.1700
Data Index: 6918198 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.7666. Min Act: -0.1700
Data Index: 1067013 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.7041. Min Act: -0.1700
Data Index: 3025393 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.6884. Min Act: -0.1700
Data Index: 54922 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.6415. Min Act: -0.1700
Data Index: 844506 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.6415. Min Act: -0.1700
Data Index: 1176629 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.6415. Min Act: -0.1700
Data Index: 265302 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.6102. Min Act: -0.1700
Data Index: 4291201 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5789. Min Act: -0.1700
Data Index: 1993852 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5476. Min Act: -0.1700
Data Index: 7029746 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5476. Min Act: -0.1700
Data Index: 8117301 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5319. Min Act: -0.1700
Data Index: 4444530 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5006. Min Act: -0.1700
Data Index: 5037837 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5006. Min Act: -0.1700
Data Index: 6612382 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5162. Min Act: -0.1700
Data Index: 5645554 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.5006. Min Act: -0.1700
Data Index: 1139669 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.4536. Min Act: -0.1700
Data Index: 5528285 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.4379. Min Act: -0.1700
Data Index: 8638423 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.4222. Min Act: -0.1700
Data Index: 2593826 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0011. Min Range: -4.0011
Max Act: 3.4066. Min Act: -0.1700
Data Index: 1987835 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19