Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4568 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.9846. Min Act: -0.1700
Data Index: 5487349 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.9221. Min Act: -0.1700
Data Index: 60904 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.9221. Min Act: -0.1700
Data Index: 3982898 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.8909. Min Act: -0.1700
Data Index: 6328192 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.8284. Min Act: -0.1700
Data Index: 4312339 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.7971. Min Act: -0.1700
Data Index: 1082008 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.6721. Min Act: -0.1700
Data Index: 5428255 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.6409. Min Act: -0.1700
Data Index: 4255098 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.6721. Min Act: -0.1700
Data Index: 4714786 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.6096. Min Act: -0.1700
Data Index: 135227 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.6096. Min Act: -0.1700
Data Index: 3983476 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.5784. Min Act: -0.1700
Data Index: 6929061 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.5784. Min Act: -0.1700
Data Index: 4264712 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.5471. Min Act: -0.1700
Data Index: 4766904 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.5159. Min Act: -0.1700
Data Index: 7510969 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.4846. Min Act: -0.1700
Data Index: 4031359 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.4846. Min Act: -0.1700
Data Index: 4192781 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.4846. Min Act: -0.1700
Data Index: 2133389 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.4846. Min Act: -0.1700
Data Index: 2616157 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9846. Min Range: -5.9846
Max Act: 5.4534. Min Act: -0.1700
Data Index: 1520086 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19