Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2640. Min Range: -9.2640
Max Act: 9.2640. Min Act: -0.1700
Data Index: 7983366 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2640. Min Range: -9.2640
Max Act: 9.2640. Min Act: -0.1700
Data Index: 7121820 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.9515. Min Act: -0.1700
Data Index: 6857890 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.8890. Min Act: -0.1700
Data Index: 3017032 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.8890. Min Act: -0.1700
Data Index: 2711684 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.8890. Min Act: -0.1700
Data Index: 5356804 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.8265. Min Act: -0.1700
Data Index: 8145161 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.7015. Min Act: -0.1700
Data Index: 1663907 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.7015. Min Act: -0.1700
Data Index: 3884034 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.5765. Min Act: -0.1700
Data Index: 6443143 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.4515. Min Act: -0.1700
Data Index: 1736770 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.3265. Min Act: -0.1700
Data Index: 6401570 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.3265. Min Act: -0.1700
Data Index: 5732444 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.2640. Min Act: -0.1700
Data Index: 7756743 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.2640. Min Act: -0.1700
Data Index: 8384037 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.2640. Min Act: -0.1700
Data Index: 6658075 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.2640. Min Act: -0.1700
Data Index: 8535103 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.2327. Min Act: -0.1700
Data Index: 865943 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.2015. Min Act: -0.1700
Data Index: 8194173 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2640. Min Range: -9.2640
Max Act: 8.1702. Min Act: -0.1700
Data Index: 3777345 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19