Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4011. Min Range: -7.4011
Max Act: 7.4011. Min Act: -0.1700
Data Index: 6996186 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4011. Min Range: -7.4011
Max Act: 7.1199. Min Act: -0.1700
Data Index: 6365479 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4011. Min Range: -7.4011
Max Act: 7.1199. Min Act: -0.1700
Data Index: 1177010 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4011. Min Range: -7.4011
Max Act: 7.1511. Min Act: -0.1700
Data Index: 1073633 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4011. Min Range: -7.4011
Max Act: 7.0886. Min Act: -0.1700
Data Index: 564786 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4011. Min Range: -7.4011
Max Act: 7.0261. Min Act: -0.1700
Data Index: 5833700 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4011. Min Range: -7.4011
Max Act: 7.0574. Min Act: -0.1700
Data Index: 4554407 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.9949. Min Act: -0.1700
Data Index: 5204320 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.9636. Min Act: -0.1700
Data Index: 4087033 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.9011. Min Act: -0.1700
Data Index: 5095043 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.8386. Min Act: -0.1700
Data Index: 34907 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.8699. Min Act: -0.1700
Data Index: 2623337 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.8074. Min Act: -0.1700
Data Index: 4403203 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.8074. Min Act: -0.1700
Data Index: 6828437 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.8074. Min Act: -0.1700
Data Index: 7577552 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.7761. Min Act: -0.1700
Data Index: 3808870 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.7136. Min Act: -0.1700
Data Index: 1358534 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.7449. Min Act: -0.1700
Data Index: 3551232 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.7449. Min Act: -0.1700
Data Index: 5076687 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4011. Min Range: -7.4011
Max Act: 6.7449. Min Act: -0.1700
Data Index: 6288511 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19