Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.3503. Min Act: -0.1700
Data Index: 5767011 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.3346. Min Act: -0.1700
Data Index: 7093751 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.3032. Min Act: -0.1700
Data Index: 8217580 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.2875. Min Act: -0.1700
Data Index: 2869410 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.2247. Min Act: -0.1700
Data Index: 4231380 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.2404. Min Act: -0.1700
Data Index: 6135619 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.2404. Min Act: -0.1700
Data Index: 1686994 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.2247. Min Act: -0.1700
Data Index: 3075612 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.2090. Min Act: -0.1700
Data Index: 8334816 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.2090. Min Act: -0.1700
Data Index: 1222057 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1775. Min Act: -0.1700
Data Index: 141200 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1775. Min Act: -0.1700
Data Index: 3469240 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1775. Min Act: -0.1700
Data Index: 1614065 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1460. Min Act: -0.1700
Data Index: 3500550 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1618. Min Act: -0.1700
Data Index: 3788697 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1618. Min Act: -0.1700
Data Index: 8016322 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1303. Min Act: -0.1700
Data Index: 6501045 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1618. Min Act: -0.1700
Data Index: 982529 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1460. Min Act: -0.1700
Data Index: 4338428 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3503. Min Range: -3.3503
Max Act: 3.1303. Min Act: -0.1700
Data Index: 6664947 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19