Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1934 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.8232. Min Act: -0.0001
Data Index: 1136961 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.8190. Min Act: -0.0001
Data Index: 243367 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.4056. Min Act: -0.0001
Data Index: 207948 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.3279. Min Act: -0.0001
Data Index: 1167032 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.2334. Min Act: -0.0001
Data Index: 185291 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.4085. Min Act: -0.0001
Data Index: 843768 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.1717. Min Act: -0.0001
Data Index: 1338639 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.3708. Min Act: -0.0001
Data Index: 962702 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.2365. Min Act: -0.0001
Data Index: 178864 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.2404. Min Act: -0.0001
Data Index: 824431 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.1311. Min Act: -0.0001
Data Index: 272897 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.1141. Min Act: -0.0001
Data Index: 502793 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.0836. Min Act: -0.0001
Data Index: 611141 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8232. Min Range: -2.8232
Max Act: 1.9787. Min Act: -0.0001
Data Index: 279846 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.1823. Min Act: -0.0001
Data Index: 318415 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.1632. Min Act: -0.0001
Data Index: 1161491 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.0390. Min Act: -0.0001
Data Index: 345428 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.1046. Min Act: -0.0001
Data Index: 1443342 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.0996. Min Act: -0.0001
Data Index: 80277 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8232. Min Range: -2.8232
Max Act: 2.0993. Min Act: -0.0001
Data Index: 1558603 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19