Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 66 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8986. Min Act: -0.1700
Data Index: 79238 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8669. Min Act: -0.1700
Data Index: 396897 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8510. Min Act: -0.1700
Data Index: 573735 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8669. Min Act: -0.1700
Data Index: 431780 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8351. Min Act: -0.1700
Data Index: 1248719 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8510. Min Act: -0.1700
Data Index: 918518 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8192. Min Act: -0.1700
Data Index: 627073 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8192. Min Act: -0.1700
Data Index: 255262 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8033. Min Act: -0.1700
Data Index: 185906 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8033. Min Act: -0.1700
Data Index: 264514 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8033. Min Act: -0.1700
Data Index: 993266 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.8033. Min Act: -0.1700
Data Index: 1239507 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7873. Min Act: -0.1700
Data Index: 828935 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7714. Min Act: -0.1700
Data Index: 473913 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7714. Min Act: -0.1700
Data Index: 460937 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7714. Min Act: -0.1700
Data Index: 416742 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7554. Min Act: -0.1700
Data Index: 95551 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7554. Min Act: -0.1700
Data Index: 988420 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7235. Min Act: -0.1700
Data Index: 418638 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8986. Min Range: -2.8986
Max Act: 2.7395. Min Act: -0.1700
Data Index: 440995 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19