Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1048 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.1023. Min Act: -0.1700
Data Index: 1301183 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.1023. Min Act: -0.1700
Data Index: 1651808 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.0708. Min Act: -0.1700
Data Index: 504732 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.0708. Min Act: -0.1700
Data Index: 1005384 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.0550. Min Act: -0.1700
Data Index: 1044852 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.0234. Min Act: -0.1700
Data Index: 646485 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.0234. Min Act: -0.1700
Data Index: 999721 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.0234. Min Act: -0.1700
Data Index: 1532909 (Python Code)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1023. Min Range: -3.1023
Max Act: 3.0076. Min Act: -0.1700
Data Index: 1377225 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9760. Min Act: -0.1700
Data Index: 1398147 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9918. Min Act: -0.1700
Data Index: 237540 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9760. Min Act: -0.1700
Data Index: 36974 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9443. Min Act: -0.1700
Data Index: 45851 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9443. Min Act: -0.1700
Data Index: 658719 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9443. Min Act: -0.1700
Data Index: 1585925 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9285. Min Act: -0.1700
Data Index: 1588967 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9601. Min Act: -0.1700
Data Index: 1373796 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9285. Min Act: -0.1700
Data Index: 883738 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9285. Min Act: -0.1700
Data Index: 988631 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1023. Min Range: -3.1023
Max Act: 2.9285. Min Act: -0.1700
Data Index: 423626 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19