Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1681 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.3879. Min Act: -0.1700
Data Index: 4137896 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.3254. Min Act: -0.1700
Data Index: 2671902 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.2941. Min Act: -0.1700
Data Index: 5109928 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.2004. Min Act: -0.1700
Data Index: 5551027 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.2004. Min Act: -0.1700
Data Index: 2282 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.1691. Min Act: -0.1700
Data Index: 1367008 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.1691. Min Act: -0.1700
Data Index: 1866020 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.1691. Min Act: -0.1700
Data Index: 6467710 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.1379. Min Act: -0.1700
Data Index: 3805900 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.1379. Min Act: -0.1700
Data Index: 7948670 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.1066. Min Act: -0.1700
Data Index: 4323349 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0754. Min Act: -0.1700
Data Index: 406136 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0754. Min Act: -0.1700
Data Index: 4483183 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0441. Min Act: -0.1700
Data Index: 6365655 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0441. Min Act: -0.1700
Data Index: 6530306 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0129. Min Act: -0.1700
Data Index: 3677722 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0129. Min Act: -0.1700
Data Index: 3832827 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0129. Min Act: -0.1700
Data Index: 4852656 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0129. Min Act: -0.1700
Data Index: 1866021 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3879. Min Range: -5.3879
Max Act: 5.0129. Min Act: -0.1700
Data Index: 5438069 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19