Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 664 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.9405. Min Act: -0.0001
Data Index: 603944 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.5344. Min Act: -0.0001
Data Index: 225515 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.6895. Min Act: -0.0001
Data Index: 799706 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.6555. Min Act: -0.0001
Data Index: 324969 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.5052. Min Act: -0.0001
Data Index: 911871 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3645. Min Act: -0.0001
Data Index: 575865 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.7019. Min Act: -0.0001
Data Index: 1024561 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.1912. Min Act: -0.0001
Data Index: 1135072 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.5426. Min Act: -0.0001
Data Index: 163639 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.5059. Min Act: -0.0001
Data Index: 302986 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3405. Min Act: -0.0001
Data Index: 83424 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.5466. Min Act: -0.0001
Data Index: 21349 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3064. Min Act: -0.0001
Data Index: 22796 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3371. Min Act: -0.0001
Data Index: 744600 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3106. Min Act: -0.0001
Data Index: 351606 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3371. Min Act: -0.0001
Data Index: 104331 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3320. Min Act: -0.0001
Data Index: 578205 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.5197. Min Act: -0.0001
Data Index: 1226609 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3888. Min Act: -0.0001
Data Index: 923468 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9405. Min Range: -2.9405
Max Act: 2.3809. Min Act: -0.0001
Data Index: 70550 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19