Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 50 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1053. Min Range: -2.1053
Max Act: 2.1053. Min Act: -0.0001
Data Index: 1329804 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.7483. Min Act: -0.0001
Data Index: 824295 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.5706. Min Act: -0.0001
Data Index: 67403 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.6221. Min Act: -0.0001
Data Index: 732950 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.4848. Min Act: -0.0001
Data Index: 227616 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.5522. Min Act: -0.0001
Data Index: 517795 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.5116. Min Act: -0.0001
Data Index: 49035 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.4116. Min Act: -0.0001
Data Index: 788920 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.4472. Min Act: -0.0001
Data Index: 123694 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3945. Min Act: -0.0001
Data Index: 865088 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3904. Min Act: -0.0001
Data Index: 155875 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3008. Min Act: -0.0001
Data Index: 1037233 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3686. Min Act: -0.0001
Data Index: 1118086 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3386. Min Act: -0.0001
Data Index: 214858 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3343. Min Act: -0.0001
Data Index: 717068 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.2904. Min Act: -0.0001
Data Index: 53270 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.2863. Min Act: -0.0001
Data Index: 912996 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3076. Min Act: -0.0001
Data Index: 1312509 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.3761. Min Act: -0.0001
Data Index: 966511 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1053. Min Range: -2.1053
Max Act: 1.2094. Min Act: -0.0001
Data Index: 1185459 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19