Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2394 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9930. Min Act: -0.1320
Data Index: 1214850 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9757. Min Act: -0.1499
Data Index: 7268608 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9584. Min Act: -0.1563
Data Index: 8470296 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9584. Min Act: -0.1570
Data Index: 1982279 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9325. Min Act: -0.1547
Data Index: 5638605 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9325. Min Act: -0.1513
Data Index: 1699067 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9325. Min Act: -0.1484
Data Index: 257284 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9325. Min Act: -0.1310
Data Index: 3537476 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9411. Min Act: -0.1700
Data Index: 4602181 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9325. Min Act: -0.1605
Data Index: 2253763 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9154. Min Act: -0.1537
Data Index: 6488007 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9239. Min Act: -0.1505
Data Index: 325001 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9239. Min Act: -0.1516
Data Index: 1188651 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9325. Min Act: -0.1557
Data Index: 5336779 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9239. Min Act: -0.1409
Data Index: 3106621 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9154. Min Act: -0.1700
Data Index: 1651159 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9154. Min Act: -0.1689
Data Index: 3400605 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9154. Min Act: -0.1540
Data Index: 8134928 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9154. Min Act: -0.1449
Data Index: 5912522 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9930. Min Range: -0.9930
Max Act: 0.9068. Min Act: -0.1633
Data Index: 1579690 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19