Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.6386. Min Act: -0.1700
Data Index: 8077244 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5833. Min Act: -0.1699
Data Index: 7612970 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5523. Min Act: -0.1699
Data Index: 5886890 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5600. Min Act: -0.1700
Data Index: 587738 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5523. Min Act: -0.1700
Data Index: 2917773 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5446. Min Act: -0.1661
Data Index: 3042701 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5446. Min Act: -0.1696
Data Index: 8481107 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5369. Min Act: -0.1690
Data Index: 5465327 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5293. Min Act: -0.1680
Data Index: 2676216 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5217. Min Act: -0.1698
Data Index: 4561070 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5217. Min Act: -0.1700
Data Index: 7105270 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.5217. Min Act: -0.1699
Data Index: 6390195 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4915. Min Act: -0.1689
Data Index: 2747389 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4915. Min Act: -0.1700
Data Index: 7985912 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4841. Min Act: -0.1700
Data Index: 3547412 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4915. Min Act: -0.1699
Data Index: 4749695 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4915. Min Act: -0.1677
Data Index: 1176709 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4915. Min Act: -0.1700
Data Index: 3930185 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4915. Min Act: -0.1699
Data Index: 3547848 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6386. Min Range: -0.6386
Max Act: 0.4841. Min Act: -0.1700
Data Index: 3670773 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19