Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4746 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4174. Min Range: -2.4174
Max Act: 2.2530. Min Act: -0.0001
Data Index: 1566226 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4174. Min Range: -2.4174
Max Act: 2.1500. Min Act: -0.0001
Data Index: 198256 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4174. Min Range: -2.4174
Max Act: 2.4174. Min Act: -0.0001
Data Index: 1522654 (Python Code)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4174. Min Range: -2.4174
Max Act: 2.0886. Min Act: -0.0001
Data Index: 1510962 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.8631. Min Act: -0.0001
Data Index: 976081 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.9786. Min Act: -0.0001
Data Index: 208538 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.8407. Min Act: -0.0001
Data Index: 561942 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.8453. Min Act: -0.0001
Data Index: 458898 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.5249. Min Act: -0.0001
Data Index: 1593707 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.8898. Min Act: -0.0001
Data Index: 397411 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.7256. Min Act: -0.0001
Data Index: 1440251 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.6267. Min Act: -0.0001
Data Index: 1152527 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4174. Min Range: -2.4174
Max Act: 2.2798. Min Act: -0.0001
Data Index: 738193 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.8839. Min Act: -0.0001
Data Index: 241871 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.8597. Min Act: -0.0001
Data Index: 1642186 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.6380. Min Act: -0.0001
Data Index: 1409963 (Python Code)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.6130. Min Act: -0.0001
Data Index: 86055 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.5816. Min Act: -0.0001
Data Index: 1440579 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.4992. Min Act: -0.0001
Data Index: 695919 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4174. Min Range: -2.4174
Max Act: 1.5727. Min Act: -0.0001
Data Index: 1342087 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19