Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4471 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1122. Min Range: -7.1122
Max Act: 7.1122. Min Act: -0.1700
Data Index: 8391969 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1122. Min Range: -7.1122
Max Act: 7.0184. Min Act: -0.1700
Data Index: 7670292 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.9559. Min Act: -0.1700
Data Index: 2099104 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.8934. Min Act: -0.1700
Data Index: 5382681 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.8309. Min Act: -0.1700
Data Index: 7326618 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.8622. Min Act: -0.1700
Data Index: 8489795 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7684. Min Act: -0.1700
Data Index: 3747475 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7684. Min Act: -0.1700
Data Index: 2883545 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7684. Min Act: -0.1700
Data Index: 1240177 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7684. Min Act: -0.1700
Data Index: 4316403 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7372. Min Act: -0.1700
Data Index: 2738083 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7372. Min Act: -0.1700
Data Index: 8347975 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7372. Min Act: -0.1700
Data Index: 1935430 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7372. Min Act: -0.1700
Data Index: 2785645 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7372. Min Act: -0.1700
Data Index: 6705291 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7059. Min Act: -0.1700
Data Index: 2133594 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7059. Min Act: -0.1700
Data Index: 6674563 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7059. Min Act: -0.1700
Data Index: 3503431 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7059. Min Act: -0.1700
Data Index: 545761 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1122. Min Range: -7.1122
Max Act: 6.7059. Min Act: -0.1700
Data Index: 3200467 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19