Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 857 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 2.2128. Min Range: -2.2128
Max Act: 2.2083. Min Act: -0.0004
Data Index: 610402 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2128. Min Range: -2.2128
Max Act: 2.2128. Min Act: -0.0004
Data Index: 1232984 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.8996. Min Act: -0.0004
Data Index: 490017 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2128. Min Range: -2.2128
Max Act: 2.0842. Min Act: -0.0004
Data Index: 201358 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2128. Min Range: -2.2128
Max Act: 2.1519. Min Act: -0.0004
Data Index: 235077 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.9891. Min Act: -0.0004
Data Index: 858985 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.6979. Min Act: -0.0004
Data Index: 180248 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7535. Min Act: -0.0004
Data Index: 858799 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7812. Min Act: -0.0004
Data Index: 980301 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.8708. Min Act: -0.0004
Data Index: 123613 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7068. Min Act: -0.0004
Data Index: 830936 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.5126. Min Act: -0.0004
Data Index: 1010826 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7540. Min Act: -0.0004
Data Index: 322633 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.9275. Min Act: -0.0004
Data Index: 351513 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.6051. Min Act: -0.0004
Data Index: 914371 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7211. Min Act: -0.0004
Data Index: 481803 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7711. Min Act: -0.0004
Data Index: 355354 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7182. Min Act: -0.0004
Data Index: 719977 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.6716. Min Act: -0.0004
Data Index: 572692 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2128. Min Range: -2.2128
Max Act: 1.7481. Min Act: -0.0004
Data Index: 1315664 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19