Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.9685. Min Act: -0.1700
Data Index: 2811482 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.9372. Min Act: -0.1700
Data Index: 5400714 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.8747. Min Act: -0.1700
Data Index: 4236803 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.7027. Min Act: -0.1700
Data Index: 2041979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.7027. Min Act: -0.1700
Data Index: 4880007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.7183. Min Act: -0.1700
Data Index: 6637260 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.6871. Min Act: -0.1700
Data Index: 7992138 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.6245. Min Act: -0.1700
Data Index: 7362674 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.6088. Min Act: -0.1700
Data Index: 7522178 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.3895. Min Act: -0.1700
Data Index: 4880021 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.3738. Min Act: -0.1700
Data Index: 3209676 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.3425. Min Act: -0.1700
Data Index: 8136561 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.3582. Min Act: -0.1700
Data Index: 5369665 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.3425. Min Act: -0.1700
Data Index: 8042839 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.3425. Min Act: -0.1700
Data Index: 4101595 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.3268. Min Act: -0.1700
Data Index: 2384207 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.2954. Min Act: -0.1700
Data Index: 1568700 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.2954. Min Act: -0.1700
Data Index: 7997403 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.2640. Min Act: -0.1700
Data Index: 6158696 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9685. Min Range: -3.9685
Max Act: 3.2640. Min Act: -0.1700
Data Index: 4229101 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19