Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1940 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.7909. Min Act: -0.1700
Data Index: 730680 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.7749. Min Act: -0.1700
Data Index: 357623 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.8068. Min Act: -0.1700
Data Index: 1179650 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.7749. Min Act: -0.1700
Data Index: 865677 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.7590. Min Act: -0.1700
Data Index: 864170 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.7270. Min Act: -0.1700
Data Index: 605336 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.7111. Min Act: -0.1700
Data Index: 179894 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.7111. Min Act: -0.1700
Data Index: 233489 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6951. Min Act: -0.1700
Data Index: 266199 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6951. Min Act: -0.1700
Data Index: 1164906 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6951. Min Act: -0.1700
Data Index: 709283 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6951. Min Act: -0.1700
Data Index: 652640 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6951. Min Act: -0.1700
Data Index: 1042597 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6630. Min Act: -0.1700
Data Index: 1025504 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6630. Min Act: -0.1700
Data Index: 224824 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6790. Min Act: -0.1700
Data Index: 33713 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6470. Min Act: -0.1700
Data Index: 920889 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6470. Min Act: -0.1700
Data Index: 152209 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6309. Min Act: -0.1700
Data Index: 323564 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8068. Min Range: -2.8068
Max Act: 2.6630. Min Act: -0.1700
Data Index: 524689 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19