Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1993 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2923. Min Act: -0.0001
Data Index: 720043 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2567. Min Act: -0.0001
Data Index: 399201 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2524. Min Act: -0.0001
Data Index: 14074 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2346. Min Act: -0.0001
Data Index: 1343092 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2139. Min Act: -0.0001
Data Index: 1319510 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2362. Min Act: -0.0001
Data Index: 679557 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2094. Min Act: -0.0001
Data Index: 191450 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2417. Min Act: -0.0001
Data Index: 775772 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2084. Min Act: -0.0001
Data Index: 670767 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2035. Min Act: -0.0001
Data Index: 882517 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2476. Min Act: -0.0001
Data Index: 500994 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2001. Min Act: -0.0001
Data Index: 1537490 (Python Code)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2108. Min Act: -0.0001
Data Index: 1196988 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2021. Min Act: -0.0001
Data Index: 103317 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.1793. Min Act: -0.0001
Data Index: 513420 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.1954. Min Act: -0.0001
Data Index: 1170116 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.1941. Min Act: -0.0001
Data Index: 108773 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.1723. Min Act: -0.0001
Data Index: 1182278 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.1928. Min Act: -0.0001
Data Index: 1006162 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2923. Min Range: -0.2923
Max Act: 0.2004. Min Act: -0.0001
Data Index: 1509598 (Python Code)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19