Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.4690. Min Act: -0.1700
Data Index: 6291072 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.4378. Min Act: -0.1700
Data Index: 3476506 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.4378. Min Act: -0.1700
Data Index: 88502 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.3128. Min Act: -0.1700
Data Index: 5715818 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.3128. Min Act: -0.1700
Data Index: 495182 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.3128. Min Act: -0.1700
Data Index: 6762754 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.2815. Min Act: -0.1700
Data Index: 309758 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.2815. Min Act: -0.1700
Data Index: 2352545 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.2190. Min Act: -0.1700
Data Index: 1790188 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.2190. Min Act: -0.1700
Data Index: 6362296 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.1878. Min Act: -0.1700
Data Index: 8086648 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.1878. Min Act: -0.1700
Data Index: 4328560 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.1878. Min Act: -0.1700
Data Index: 1952202 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.1253. Min Act: -0.1700
Data Index: 5974843 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.1253. Min Act: -0.1700
Data Index: 6777600 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.1253. Min Act: -0.1700
Data Index: 8452795 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.0940. Min Act: -0.1700
Data Index: 2669073 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.0940. Min Act: -0.1700
Data Index: 5363132 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.0940. Min Act: -0.1700
Data Index: 6779200 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4690. Min Range: -6.4690
Max Act: 6.0940. Min Act: -0.1700
Data Index: 277596 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19