Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2019 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.4867. Min Act: -0.1700
Data Index: 908633 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.4242. Min Act: -0.1700
Data Index: 1273044 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.3930. Min Act: -0.1700
Data Index: 561865 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.3305. Min Act: -0.1700
Data Index: 185504 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.2992. Min Act: -0.1700
Data Index: 398929 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.2992. Min Act: -0.1700
Data Index: 957819 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.2054. Min Act: -0.1700
Data Index: 1121718 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.2054. Min Act: -0.1700
Data Index: 622215 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.2054. Min Act: -0.1700
Data Index: 58054 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.0804. Min Act: -0.1700
Data Index: 676326 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.1117. Min Act: -0.1700
Data Index: 691857 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.1117. Min Act: -0.1700
Data Index: 158836 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.1117. Min Act: -0.1700
Data Index: 8975 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.0804. Min Act: -0.1700
Data Index: 423076 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.0804. Min Act: -0.1700
Data Index: 78589 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.0179. Min Act: -0.1700
Data Index: 1126197 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4867. Min Range: -4.4867
Max Act: 4.0179. Min Act: -0.1700
Data Index: 938759 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4867. Min Range: -4.4867
Max Act: 3.9866. Min Act: -0.1700
Data Index: 1113752 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4867. Min Range: -4.4867
Max Act: 3.9554. Min Act: -0.1700
Data Index: 1559960 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4867. Min Range: -4.4867
Max Act: 3.9554. Min Act: -0.1700
Data Index: 363873 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19