Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5569 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5196. Min Range: -8.5196
Max Act: 8.5196. Min Act: -0.1700
Data Index: 8019413 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.8321. Min Act: -0.1700
Data Index: 5450944 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.8009. Min Act: -0.1700
Data Index: 6279936 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.6759. Min Act: -0.1700
Data Index: 5287744 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.6134. Min Act: -0.1700
Data Index: 1583020 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.5509. Min Act: -0.1700
Data Index: 4211127 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4884. Min Act: -0.1700
Data Index: 4482395 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4884. Min Act: -0.1700
Data Index: 1310357 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4884. Min Act: -0.1700
Data Index: 5616536 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4571. Min Act: -0.1700
Data Index: 793814 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4259. Min Act: -0.1700
Data Index: 7060554 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4259. Min Act: -0.1700
Data Index: 6884152 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4259. Min Act: -0.1700
Data Index: 4289413 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.3634. Min Act: -0.1700
Data Index: 7927377 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.4259. Min Act: -0.1700
Data Index: 8357948 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.3946. Min Act: -0.1700
Data Index: 1609298 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.3321. Min Act: -0.1700
Data Index: 273255 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.3321. Min Act: -0.1700
Data Index: 4679690 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.3009. Min Act: -0.1700
Data Index: 3556110 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5196. Min Range: -8.5196
Max Act: 7.3009. Min Act: -0.1700
Data Index: 936814 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19