Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1756 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5196. Min Range: -6.5196
Max Act: 6.5196. Min Act: -0.1700
Data Index: 1259325 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5196. Min Range: -6.5196
Max Act: 6.3946. Min Act: -0.1700
Data Index: 4481347 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5196. Min Range: -6.5196
Max Act: 6.3321. Min Act: -0.1700
Data Index: 6243861 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5196. Min Range: -6.5196
Max Act: 6.1446. Min Act: -0.1700
Data Index: 6548132 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5196. Min Range: -6.5196
Max Act: 6.0196. Min Act: -0.1700
Data Index: 7994085 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.9883. Min Act: -0.1700
Data Index: 1233118 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.9258. Min Act: -0.1700
Data Index: 8337913 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.8946. Min Act: -0.1700
Data Index: 37964 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.8633. Min Act: -0.1700
Data Index: 1333394 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.8633. Min Act: -0.1700
Data Index: 7577195 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.8321. Min Act: -0.1700
Data Index: 7544252 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7383. Min Act: -0.1700
Data Index: 3042019 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7383. Min Act: -0.1700
Data Index: 3824081 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7071. Min Act: -0.1700
Data Index: 794231 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7071. Min Act: -0.1700
Data Index: 36089 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7071. Min Act: -0.1700
Data Index: 1523244 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7383. Min Act: -0.1700
Data Index: 725007 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7071. Min Act: -0.1700
Data Index: 5789373 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.6758. Min Act: -0.1700
Data Index: 1243973 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5196. Min Range: -6.5196
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3125127 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19