Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 112 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.9424. Min Act: -0.1700
Data Index: 4964387 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7861. Min Act: -0.1700
Data Index: 2066889 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7861. Min Act: -0.1700
Data Index: 3874744 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7861. Min Act: -0.1700
Data Index: 1610982 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7236. Min Act: -0.1700
Data Index: 2557685 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7549. Min Act: -0.1700
Data Index: 803382 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7236. Min Act: -0.1700
Data Index: 121966 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6924. Min Act: -0.1700
Data Index: 8169848 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7236. Min Act: -0.1700
Data Index: 3504130 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6924. Min Act: -0.1700
Data Index: 4228843 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6924. Min Act: -0.1700
Data Index: 5393828 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6924. Min Act: -0.1700
Data Index: 5053907 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.7236. Min Act: -0.1700
Data Index: 3792742 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6924. Min Act: -0.1700
Data Index: 8387466 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6924. Min Act: -0.1700
Data Index: 7205220 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6611. Min Act: -0.1700
Data Index: 3796815 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6611. Min Act: -0.1700
Data Index: 1447953 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6611. Min Act: -0.1700
Data Index: 5956322 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6299. Min Act: -0.1700
Data Index: 6171853 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9424. Min Range: -4.9424
Max Act: 4.6299. Min Act: -0.1700
Data Index: 2159973 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19