Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2695 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.7777. Min Act: -0.0001
Data Index: 197661 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.6411. Min Act: -0.0000
Data Index: 1228741 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.6411. Min Act: -0.0001
Data Index: 647909 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.7101. Min Act: -0.0001
Data Index: 219840 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.4118. Min Act: -0.0001
Data Index: 637858 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.5956. Min Act: -0.0001
Data Index: 58982 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.0009. Min Act: -0.0001
Data Index: 1001240 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.9806. Min Act: -0.0001
Data Index: 554569 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.1399. Min Act: -0.0001
Data Index: 749223 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.0972. Min Act: -0.0001
Data Index: 998246 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.0134. Min Act: -0.0001
Data Index: 1009408 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.0962. Min Act: -0.0001
Data Index: 1037105 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7777. Min Range: -2.7777
Max Act: 2.0184. Min Act: -0.0001
Data Index: 14131 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.6371. Min Act: -0.0001
Data Index: 348898 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.8877. Min Act: -0.0000
Data Index: 57750 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.7715. Min Act: -0.0001
Data Index: 1233474 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.8248. Min Act: -0.0001
Data Index: 1206462 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.8922. Min Act: -0.0001
Data Index: 1296057 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.6812. Min Act: -0.0001
Data Index: 1013327 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7777. Min Range: -2.7777
Max Act: 1.7777. Min Act: -0.0001
Data Index: 31303 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19