Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1257. Min Range: -5.1257
Max Act: 5.1257. Min Act: -0.1700
Data Index: 836601 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1257. Min Range: -5.1257
Max Act: 5.0007. Min Act: -0.1700
Data Index: 3989265 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1257. Min Range: -5.1257
Max Act: 5.0007. Min Act: -0.1700
Data Index: 8178888 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1257. Min Range: -5.1257
Max Act: 5.0007. Min Act: -0.1700
Data Index: 7807507 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.9382. Min Act: -0.1700
Data Index: 833727 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.9694. Min Act: -0.1700
Data Index: 7046162 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.9694. Min Act: -0.1700
Data Index: 8306869 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4319804 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.9069. Min Act: -0.1700
Data Index: 3346889 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.9069. Min Act: -0.1700
Data Index: 812110 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8757. Min Act: -0.1700
Data Index: 433867 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.9069. Min Act: -0.1700
Data Index: 60542 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8757. Min Act: -0.1700
Data Index: 451313 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8757. Min Act: -0.1700
Data Index: 4865316 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8757. Min Act: -0.1700
Data Index: 6522529 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8757. Min Act: -0.1700
Data Index: 8267509 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8444. Min Act: -0.1700
Data Index: 8129636 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8444. Min Act: -0.1700
Data Index: 924259 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8132. Min Act: -0.1700
Data Index: 2944225 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1257. Min Range: -5.1257
Max Act: 4.8132. Min Act: -0.1700
Data Index: 6708930 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19