Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2602 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.7235. Min Act: -0.0001
Data Index: 826117 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.7705. Min Act: -0.0001
Data Index: 836303 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.7992. Min Act: -0.0001
Data Index: 710617 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.7295. Min Act: -0.0001
Data Index: 160001 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6981. Min Act: -0.0001
Data Index: 1355605 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.7100. Min Act: -0.0001
Data Index: 1252268 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.7217. Min Act: -0.0001
Data Index: 569881 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6555. Min Act: -0.0001
Data Index: 1205458 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6900. Min Act: -0.0001
Data Index: 48167 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6427. Min Act: -0.0001
Data Index: 779614 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.7446. Min Act: -0.0001
Data Index: 1069047 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6760. Min Act: -0.0001
Data Index: 960337 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6721. Min Act: -0.0001
Data Index: 1235205 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.5599. Min Act: -0.0001
Data Index: 1178937 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6133. Min Act: -0.0001
Data Index: 251313 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.5970. Min Act: -0.0001
Data Index: 1115748 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6437. Min Act: -0.0001
Data Index: 348643 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.5843. Min Act: -0.0001
Data Index: 996077 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6178. Min Act: -0.0001
Data Index: 1180545 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7992. Min Range: -0.7992
Max Act: 0.6599. Min Act: -0.0001
Data Index: 525405 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19