Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0681. Min Range: -7.0681
Max Act: 7.0681. Min Act: -0.1700
Data Index: 1346854 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.8181. Min Act: -0.1700
Data Index: 6636035 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.6931. Min Act: -0.1700
Data Index: 2312816 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.5369. Min Act: -0.1700
Data Index: 3618067 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.5369. Min Act: -0.1700
Data Index: 7475439 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.5056. Min Act: -0.1700
Data Index: 5697990 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.4744. Min Act: -0.1700
Data Index: 5428007 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.4744. Min Act: -0.1700
Data Index: 4237645 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.3806. Min Act: -0.1700
Data Index: 769498 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.3494. Min Act: -0.1700
Data Index: 2997229 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.3181. Min Act: -0.1700
Data Index: 3187015 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.3181. Min Act: -0.1700
Data Index: 5777413 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.3181. Min Act: -0.1700
Data Index: 8444715 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.2556. Min Act: -0.1700
Data Index: 4402324 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.2869. Min Act: -0.1700
Data Index: 3434777 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.2869. Min Act: -0.1700
Data Index: 1271447 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.2869. Min Act: -0.1700
Data Index: 8178519 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.2869. Min Act: -0.1700
Data Index: 8006740 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.2869. Min Act: -0.1700
Data Index: 4883438 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0681. Min Range: -7.0681
Max Act: 6.2869. Min Act: -0.1700
Data Index: 5637327 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19