Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.6613. Min Act: -0.1700
Data Index: 8498635 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.6301. Min Act: -0.1700
Data Index: 6103834 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.5051. Min Act: -0.1700
Data Index: 3105034 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.5051. Min Act: -0.1700
Data Index: 4243573 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.5051. Min Act: -0.1700
Data Index: 3150339 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4738. Min Act: -0.1700
Data Index: 1011042 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4738. Min Act: -0.1700
Data Index: 8498637 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4738. Min Act: -0.1700
Data Index: 7870479 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4426. Min Act: -0.1700
Data Index: 4608164 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4426. Min Act: -0.1700
Data Index: 5960740 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4426. Min Act: -0.1700
Data Index: 7729996 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4113. Min Act: -0.1700
Data Index: 3234787 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.4113. Min Act: -0.1700
Data Index: 7893910 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.3801. Min Act: -0.1700
Data Index: 1193953 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2577667 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.3801. Min Act: -0.1700
Data Index: 1011038 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.3801. Min Act: -0.1700
Data Index: 3259258 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.3801. Min Act: -0.1700
Data Index: 4628371 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.3801. Min Act: -0.1700
Data Index: 4778342 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6613. Min Range: -5.6613
Max Act: 5.3801. Min Act: -0.1700
Data Index: 1050010 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19