Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3438 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.8535. Min Act: -0.0001
Data Index: 821724 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.3968. Min Act: -0.0001
Data Index: 1108473 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2506. Min Act: -0.0001
Data Index: 604186 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.4539. Min Act: -0.0001
Data Index: 700098 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2360. Min Act: -0.0001
Data Index: 1158103 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.3789. Min Act: -0.0001
Data Index: 838156 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2597. Min Act: -0.0001
Data Index: 830295 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.1809. Min Act: -0.0001
Data Index: 953352 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.3678. Min Act: -0.0001
Data Index: 1023938 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2854. Min Act: -0.0001
Data Index: 1277301 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2953. Min Act: -0.0001
Data Index: 819070 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.0823. Min Act: -0.0001
Data Index: 621025 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.3596. Min Act: -0.0001
Data Index: 584578 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.3113. Min Act: -0.0001
Data Index: 103122 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.3274. Min Act: -0.0001
Data Index: 1085054 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.3359. Min Act: -0.0001
Data Index: 839210 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2064. Min Act: -0.0001
Data Index: 721591 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2397. Min Act: -0.0001
Data Index: 1165564 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.1841. Min Act: -0.0001
Data Index: 1280165 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8535. Min Range: -1.8535
Max Act: 1.2179. Min Act: -0.0001
Data Index: 634559 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19