Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.8333. Min Act: -0.1700
Data Index: 931875 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.8020. Min Act: -0.1700
Data Index: 6772091 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.5520. Min Act: -0.1700
Data Index: 2600599 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.4583. Min Act: -0.1700
Data Index: 2088118 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.3645. Min Act: -0.1700
Data Index: 7958029 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.3020. Min Act: -0.1700
Data Index: 8804210 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.3020. Min Act: -0.1700
Data Index: 8484138 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.3020. Min Act: -0.1700
Data Index: 2755158 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.2395. Min Act: -0.1700
Data Index: 1768374 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.2395. Min Act: -0.1700
Data Index: 7541201 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1770. Min Act: -0.1700
Data Index: 2700671 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1458. Min Act: -0.1700
Data Index: 1919173 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.2083. Min Act: -0.1700
Data Index: 1866500 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1458. Min Act: -0.1700
Data Index: 5261185 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1458. Min Act: -0.1700
Data Index: 3584020 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1458. Min Act: -0.1700
Data Index: 2801101 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.0833. Min Act: -0.1700
Data Index: 1164892 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1145. Min Act: -0.1700
Data Index: 5369836 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1145. Min Act: -0.1700
Data Index: 2028225 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8333. Min Range: -7.8333
Max Act: 7.1458. Min Act: -0.1700
Data Index: 6990079 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19