Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4038 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.8992. Min Act: -0.0001
Data Index: 282165 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.8503. Min Act: -0.0001
Data Index: 489838 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.8305. Min Act: -0.0001
Data Index: 807569 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.8078. Min Act: -0.0001
Data Index: 693117 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7564. Min Act: -0.0001
Data Index: 584917 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7907. Min Act: -0.0001
Data Index: 640593 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7171. Min Act: -0.0001
Data Index: 901347 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7376. Min Act: -0.0001
Data Index: 869631 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7395. Min Act: -0.0001
Data Index: 1241461 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7594. Min Act: -0.0001
Data Index: 661735 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7360. Min Act: -0.0001
Data Index: 1253169 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7593. Min Act: -0.0001
Data Index: 934147 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7824. Min Act: -0.0001
Data Index: 254331 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7174. Min Act: -0.0001
Data Index: 220917 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7399. Min Act: -0.0001
Data Index: 1285143 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7399. Min Act: -0.0001
Data Index: 770812 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7601. Min Act: -0.0001
Data Index: 1237110 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7336. Min Act: -0.0001
Data Index: 1293812 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7134. Min Act: -0.0001
Data Index: 1081267 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8992. Min Range: -0.8992
Max Act: 0.7125. Min Act: -0.0001
Data Index: 680301 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19