Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2640. Min Range: -6.2640
Max Act: 6.2640. Min Act: -0.1700
Data Index: 3329338 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2640. Min Range: -6.2640
Max Act: 6.2640. Min Act: -0.1700
Data Index: 5683667 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2640. Min Range: -6.2640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 128551 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2640. Min Range: -6.2640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 384517 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2640. Min Range: -6.2640
Max Act: 6.0765. Min Act: -0.1700
Data Index: 5447792 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2640. Min Range: -6.2640
Max Act: 6.0453. Min Act: -0.1700
Data Index: 481470 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2640. Min Range: -6.2640
Max Act: 6.0140. Min Act: -0.1700
Data Index: 2548418 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.9828. Min Act: -0.1700
Data Index: 2228217 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8890. Min Act: -0.1700
Data Index: 2117372 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8890. Min Act: -0.1700
Data Index: 2564624 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8578. Min Act: -0.1700
Data Index: 5272953 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8578. Min Act: -0.1700
Data Index: 1329722 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8578. Min Act: -0.1700
Data Index: 4371338 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8578. Min Act: -0.1700
Data Index: 3463506 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8265. Min Act: -0.1700
Data Index: 2269664 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8265. Min Act: -0.1700
Data Index: 2058072 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.8265. Min Act: -0.1700
Data Index: 6478656 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.7953. Min Act: -0.1700
Data Index: 7009099 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.7640. Min Act: -0.1700
Data Index: 5261260 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2640. Min Range: -6.2640
Max Act: 5.7640. Min Act: -0.1700
Data Index: 7073250 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19