Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9475. Min Range: -8.9475
Max Act: 8.9475. Min Act: -0.1700
Data Index: 5047444 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9475. Min Range: -8.9475
Max Act: 8.3225. Min Act: -0.1700
Data Index: 6025083 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9475. Min Range: -8.9475
Max Act: 8.0100. Min Act: -0.1700
Data Index: 5041217 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9475. Min Range: -8.9475
Max Act: 8.0100. Min Act: -0.1700
Data Index: 7753431 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.9787. Min Act: -0.1700
Data Index: 2468106 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.9787. Min Act: -0.1700
Data Index: 7504382 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.9162. Min Act: -0.1700
Data Index: 1161858 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.8850. Min Act: -0.1700
Data Index: 4862224 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.8850. Min Act: -0.1700
Data Index: 6575322 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.8225. Min Act: -0.1700
Data Index: 6477314 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.7600. Min Act: -0.1700
Data Index: 7567778 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.7600. Min Act: -0.1700
Data Index: 6747962 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.7287. Min Act: -0.1700
Data Index: 1192334 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.7287. Min Act: -0.1700
Data Index: 2034028 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.7287. Min Act: -0.1700
Data Index: 2172541 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.6975. Min Act: -0.1700
Data Index: 7414475 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.6662. Min Act: -0.1700
Data Index: 630088 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.6975. Min Act: -0.1700
Data Index: 5524811 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.6037. Min Act: -0.1700
Data Index: 5029604 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9475. Min Range: -8.9475
Max Act: 7.6037. Min Act: -0.1700
Data Index: 4235809 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19