Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1160 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.4685. Min Act: -0.1700
Data Index: 363895 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.4059. Min Act: -0.1700
Data Index: 825934 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.3434. Min Act: -0.1700
Data Index: 126895 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.3122. Min Act: -0.1700
Data Index: 632345 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2184. Min Act: -0.1700
Data Index: 525703 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.3122. Min Act: -0.1700
Data Index: 174181 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.3122. Min Act: -0.1700
Data Index: 71894 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2809. Min Act: -0.1700
Data Index: 1246350 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2497. Min Act: -0.1700
Data Index: 1123597 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.3122. Min Act: -0.1700
Data Index: 615898 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2497. Min Act: -0.1700
Data Index: 759797 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2497. Min Act: -0.1700
Data Index: 69442 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2184. Min Act: -0.1700
Data Index: 1283962 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2809. Min Act: -0.1700
Data Index: 655233 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.1872. Min Act: -0.1700
Data Index: 622907 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.1872. Min Act: -0.1700
Data Index: 579573 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2184. Min Act: -0.1700
Data Index: 961084 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2497. Min Act: -0.1700
Data Index: 965967 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.2184. Min Act: -0.1700
Data Index: 1245736 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4685. Min Range: -4.4685
Max Act: 4.1559. Min Act: -0.1700
Data Index: 1006425 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19