Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2425 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 4986632 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 6416220 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 3697730 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 1720489 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.3474. Min Act: -0.1700
Data Index: 8690327 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.2537. Min Act: -0.1700
Data Index: 4581696 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.1287. Min Act: -0.1700
Data Index: 7474661 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.1599. Min Act: -0.1700
Data Index: 4020045 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0974. Min Act: -0.1700
Data Index: 5250632 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0974. Min Act: -0.1700
Data Index: 1372508 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0662. Min Act: -0.1700
Data Index: 2858979 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0662. Min Act: -0.1700
Data Index: 1264384 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0349. Min Act: -0.1700
Data Index: 6049238 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0037. Min Act: -0.1700
Data Index: 7291119 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0037. Min Act: -0.1700
Data Index: 3662513 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0037. Min Act: -0.1700
Data Index: 3945473 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4412. Min Range: -5.4412
Max Act: 5.0037. Min Act: -0.1700
Data Index: 1834112 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4412. Min Range: -5.4412
Max Act: 4.9724. Min Act: -0.1700
Data Index: 7222993 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4412. Min Range: -5.4412
Max Act: 4.9724. Min Act: -0.1700
Data Index: 6245233 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4412. Min Range: -5.4412
Max Act: 4.9724. Min Act: -0.1700
Data Index: 6465321 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19