Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4343. Min Range: -8.4343
Max Act: 8.4343. Min Act: -0.1700
Data Index: 4892466 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4343. Min Range: -8.4343
Max Act: 8.2468. Min Act: -0.1700
Data Index: 3218658 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4343. Min Range: -8.4343
Max Act: 8.1843. Min Act: -0.1700
Data Index: 6327583 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4343. Min Range: -8.4343
Max Act: 8.1218. Min Act: -0.1700
Data Index: 6603808 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4343. Min Range: -8.4343
Max Act: 8.1218. Min Act: -0.1700
Data Index: 4364884 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4343. Min Range: -8.4343
Max Act: 8.1218. Min Act: -0.1700
Data Index: 2080445 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.9968. Min Act: -0.1700
Data Index: 2926988 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.9968. Min Act: -0.1700
Data Index: 5125052 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.9968. Min Act: -0.1700
Data Index: 6438240 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.9343. Min Act: -0.1700
Data Index: 6820987 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.9031. Min Act: -0.1700
Data Index: 702716 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.8718. Min Act: -0.1700
Data Index: 6812131 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.8718. Min Act: -0.1700
Data Index: 5569797 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.8718. Min Act: -0.1700
Data Index: 2199851 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.8406. Min Act: -0.1700
Data Index: 4614415 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.8406. Min Act: -0.1700
Data Index: 6967534 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.8718. Min Act: -0.1700
Data Index: 2473303 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.8093. Min Act: -0.1700
Data Index: 3688804 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.7468. Min Act: -0.1700
Data Index: 2592503 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4343. Min Range: -8.4343
Max Act: 7.7781. Min Act: -0.1700
Data Index: 4535278 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19