Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 165 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.7871. Min Act: -0.1700
Data Index: 514039 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.7871. Min Act: -0.1700
Data Index: 46520 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.7392. Min Act: -0.1700
Data Index: 409785 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.6913. Min Act: -0.1700
Data Index: 152621 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.6592. Min Act: -0.1700
Data Index: 139879 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.6432. Min Act: -0.1700
Data Index: 402229 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.6271. Min Act: -0.1700
Data Index: 691762 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.6271. Min Act: -0.1700
Data Index: 1089745 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.6271. Min Act: -0.1700
Data Index: 1048395 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.6110. Min Act: -0.1700
Data Index: 934107 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5950. Min Act: -0.1700
Data Index: 93265 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5950. Min Act: -0.1700
Data Index: 344481 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5789. Min Act: -0.1700
Data Index: 777796 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5789. Min Act: -0.1700
Data Index: 1108682 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5789. Min Act: -0.1700
Data Index: 691477 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5627. Min Act: -0.1700
Data Index: 113762 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5789. Min Act: -0.1700
Data Index: 960831 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5789. Min Act: -0.1700
Data Index: 654770 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5627. Min Act: -0.1700
Data Index: 78915 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7871. Min Range: -2.7871
Max Act: 2.5627. Min Act: -0.1700
Data Index: 203500 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19