Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.8385. Min Act: -0.1700
Data Index: 6855075 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.7760. Min Act: -0.1700
Data Index: 7963080 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.5573. Min Act: -0.1700
Data Index: 7423579 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3698. Min Act: -0.1700
Data Index: 3928715 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3385. Min Act: -0.1700
Data Index: 1462767 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.3073. Min Act: -0.1700
Data Index: 7180987 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.2760. Min Act: -0.1700
Data Index: 7316454 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.2135. Min Act: -0.1700
Data Index: 6785871 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.2135. Min Act: -0.1700
Data Index: 2066443 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.2135. Min Act: -0.1700
Data Index: 4030916 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.2135. Min Act: -0.1700
Data Index: 3803805 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.0885. Min Act: -0.1700
Data Index: 3982078 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.1510. Min Act: -0.1700
Data Index: 6216054 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.1510. Min Act: -0.1700
Data Index: 7277288 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.0885. Min Act: -0.1700
Data Index: 3105146 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.1198. Min Act: -0.1700
Data Index: 4078247 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.1198. Min Act: -0.1700
Data Index: 1795059 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.1198. Min Act: -0.1700
Data Index: 4046359 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.1198. Min Act: -0.1700
Data Index: 6788592 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8385. Min Range: -5.8385
Max Act: 5.0885. Min Act: -0.1700
Data Index: 1666574 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19