Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1763. Min Range: -5.1763
Max Act: 5.1763. Min Act: -0.1700
Data Index: 3977909 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1763. Min Range: -5.1763
Max Act: 5.1450. Min Act: -0.1700
Data Index: 5768368 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1763. Min Range: -5.1763
Max Act: 5.0825. Min Act: -0.1700
Data Index: 6887881 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1763. Min Range: -5.1763
Max Act: 5.0513. Min Act: -0.1700
Data Index: 8729760 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1763. Min Range: -5.1763
Max Act: 5.0200. Min Act: -0.1700
Data Index: 1821923 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1763. Min Range: -5.1763
Max Act: 5.0200. Min Act: -0.1700
Data Index: 8563210 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1763. Min Range: -5.1763
Max Act: 5.0200. Min Act: -0.1700
Data Index: 240335 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9888. Min Act: -0.1700
Data Index: 713353 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9575. Min Act: -0.1700
Data Index: 755365 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9888. Min Act: -0.1700
Data Index: 8500650 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9575. Min Act: -0.1700
Data Index: 6923764 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9263. Min Act: -0.1700
Data Index: 1154935 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9575. Min Act: -0.1700
Data Index: 6887878 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9263. Min Act: -0.1700
Data Index: 8631618 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.9263. Min Act: -0.1700
Data Index: 8381947 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.8950. Min Act: -0.1700
Data Index: 823677 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.8950. Min Act: -0.1700
Data Index: 4006446 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.8950. Min Act: -0.1700
Data Index: 4581359 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.8950. Min Act: -0.1700
Data Index: 202397 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1763. Min Range: -5.1763
Max Act: 4.8950. Min Act: -0.1700
Data Index: 6777791 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19