Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2893 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.8961. Min Act: -0.0001
Data Index: 1087431 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.8797. Min Act: -0.0001
Data Index: 848796 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.8606. Min Act: -0.0001
Data Index: 1149278 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.7097. Min Act: -0.0001
Data Index: 850593 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.7265. Min Act: -0.0001
Data Index: 1240476 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6728. Min Act: -0.0001
Data Index: 1141117 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6116. Min Act: -0.0001
Data Index: 157957 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6811. Min Act: -0.0001
Data Index: 469166 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6958. Min Act: -0.0001
Data Index: 791221 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6591. Min Act: -0.0001
Data Index: 445353 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6377. Min Act: -0.0001
Data Index: 1594143 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6806. Min Act: -0.0001
Data Index: 1326907 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6588. Min Act: -0.0001
Data Index: 1225609 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6024. Min Act: -0.0001
Data Index: 1099762 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.5871. Min Act: -0.0001
Data Index: 85241 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6363. Min Act: -0.0001
Data Index: 447585 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6372. Min Act: -0.0001
Data Index: 1159018 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.5469. Min Act: -0.0001
Data Index: 754168 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.5709. Min Act: -0.0001
Data Index: 854134 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8961. Min Range: -0.8961
Max Act: 0.6384. Min Act: -0.0001
Data Index: 100352 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19