Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.5481. Min Act: -0.1700
Data Index: 4841727 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.4346. Min Act: -0.1700
Data Index: 8142296 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.4184. Min Act: -0.1700
Data Index: 5638658 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.3366. Min Act: -0.1700
Data Index: 3179797 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.3366. Min Act: -0.1700
Data Index: 8830161 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.3366. Min Act: -0.1700
Data Index: 4420917 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2873. Min Act: -0.1700
Data Index: 4153888 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.3038. Min Act: -0.1700
Data Index: 847212 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2708. Min Act: -0.1700
Data Index: 1606076 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2708. Min Act: -0.1700
Data Index: 7661199 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2708. Min Act: -0.1700
Data Index: 4579572 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2873. Min Act: -0.1700
Data Index: 902589 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2873. Min Act: -0.1700
Data Index: 4917278 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2873. Min Act: -0.1700
Data Index: 2187455 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2708. Min Act: -0.1700
Data Index: 8370337 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2543. Min Act: -0.1699
Data Index: 1412382 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2873. Min Act: -0.1700
Data Index: 3102418 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2873. Min Act: -0.1700
Data Index: 4367135 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2708. Min Act: -0.1700
Data Index: 3178284 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5481. Min Range: -2.5481
Max Act: 2.2543. Min Act: -0.1700
Data Index: 7258503 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19