Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2283 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0359. Min Range: -10.0359
Max Act: 10.0359. Min Act: -0.1700
Data Index: 6541331 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.9109. Min Act: -0.1700
Data Index: 1394111 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.9109. Min Act: -0.1700
Data Index: 6292854 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.9109. Min Act: -0.1700
Data Index: 1917974 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.8484. Min Act: -0.1700
Data Index: 2398117 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.7234. Min Act: -0.1700
Data Index: 7427711 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.5359. Min Act: -0.1700
Data Index: 5054960 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.3484. Min Act: -0.1700
Data Index: 7789112 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.3484. Min Act: -0.1700
Data Index: 5052772 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.2859. Min Act: -0.1700
Data Index: 1170792 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.2859. Min Act: -0.1700
Data Index: 3584732 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.2234. Min Act: -0.1700
Data Index: 1667022 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.2234. Min Act: -0.1700
Data Index: 862826 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.1609. Min Act: -0.1700
Data Index: 6076337 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.0984. Min Act: -0.1700
Data Index: 80446 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.0984. Min Act: -0.1700
Data Index: 4020954 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.0359. Min Act: -0.1700
Data Index: 6611645 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.0359. Min Act: -0.1700
Data Index: 8612829 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0359. Min Range: -10.0359
Max Act: 9.0359. Min Act: -0.1700
Data Index: 3858980 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0359. Min Range: -10.0359
Max Act: 8.9734. Min Act: -0.1700
Data Index: 6228951 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19