Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4839. Min Range: -9.4839
Max Act: 9.4839. Min Act: -0.1700
Data Index: 7396122 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4839. Min Range: -9.4839
Max Act: 9.2964. Min Act: -0.1700
Data Index: 8330719 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4839. Min Range: -9.4839
Max Act: 9.2339. Min Act: -0.1700
Data Index: 4474035 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4839. Min Range: -9.4839
Max Act: 9.0464. Min Act: -0.1700
Data Index: 6325636 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.9214. Min Act: -0.1700
Data Index: 1763575 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.9839. Min Act: -0.1700
Data Index: 8363237 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.9214. Min Act: -0.1700
Data Index: 1222364 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.8589. Min Act: -0.1700
Data Index: 8348476 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.7339. Min Act: -0.1700
Data Index: 4498393 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.7339. Min Act: -0.1700
Data Index: 8151787 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.7964. Min Act: -0.1700
Data Index: 16874 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.6089. Min Act: -0.1700
Data Index: 2025976 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.6714. Min Act: -0.1700
Data Index: 6412398 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.6714. Min Act: -0.1700
Data Index: 7244703 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.5464. Min Act: -0.1700
Data Index: 1089349 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.6089. Min Act: -0.1700
Data Index: 8580936 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.6089. Min Act: -0.1700
Data Index: 7187359 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.5464. Min Act: -0.1700
Data Index: 2337231 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.4839. Min Act: -0.1700
Data Index: 5521861 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4839. Min Range: -9.4839
Max Act: 8.4839. Min Act: -0.1700
Data Index: 7605697 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19