Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4430 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.5907. Min Act: -0.0001
Data Index: 328044 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.4646. Min Act: -0.0001
Data Index: 1199608 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1827. Min Act: -0.0001
Data Index: 148594 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.2228. Min Act: -0.0001
Data Index: 120744 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.2009. Min Act: -0.0001
Data Index: 1322291 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1930. Min Act: -0.0001
Data Index: 198047 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1935. Min Act: -0.0001
Data Index: 597219 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.2375. Min Act: -0.0001
Data Index: 112527 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.0328. Min Act: -0.0001
Data Index: 1007491 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1195. Min Act: -0.0001
Data Index: 1086198 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1731. Min Act: -0.0001
Data Index: 821657 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.0338. Min Act: -0.0001
Data Index: 22388 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.0684. Min Act: -0.0001
Data Index: 29492 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1617. Min Act: -0.0001
Data Index: 158649 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1372. Min Act: -0.0001
Data Index: 866317 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.1354. Min Act: -0.0001
Data Index: 1157952 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.0061. Min Act: -0.0001
Data Index: 780864 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5907. Min Range: -1.5907
Max Act: 1.0018. Min Act: -0.0001
Data Index: 363536 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5907. Min Range: -1.5907
Max Act: 0.9965. Min Act: -0.0001
Data Index: 1318203 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5907. Min Range: -1.5907
Max Act: 0.9175. Min Act: -0.0001
Data Index: 603619 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19