Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 52 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.7227. Min Range: -3.7227
Max Act: 3.7227. Min Act: -0.0001
Data Index: 1183381 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7227. Min Range: -3.7227
Max Act: 3.2447. Min Act: -0.0001
Data Index: 794915 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7227. Min Range: -3.7227
Max Act: 3.1580. Min Act: -0.0001
Data Index: 1154371 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7227. Min Range: -3.7227
Max Act: 3.1001. Min Act: -0.0001
Data Index: 1141466 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.8999. Min Act: -0.0001
Data Index: 1305753 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.8765. Min Act: -0.0001
Data Index: 979879 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.6525. Min Act: -0.0001
Data Index: 1129627 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.9077. Min Act: -0.0001
Data Index: 456078 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.3360. Min Act: -0.0001
Data Index: 720370 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.5564. Min Act: -0.0001
Data Index: 508612 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.5513. Min Act: -0.0001
Data Index: 1127467 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.6158. Min Act: -0.0001
Data Index: 87383 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.7959. Min Act: -0.0001
Data Index: 1302624 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.6215. Min Act: -0.0001
Data Index: 463101 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.6006. Min Act: -0.0001
Data Index: 1045149 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.5626. Min Act: -0.0001
Data Index: 321375 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.4083. Min Act: -0.0001
Data Index: 691485 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.3698. Min Act: -0.0001
Data Index: 1092953 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.1319. Min Act: -0.0001
Data Index: 217882 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7227. Min Range: -3.7227
Max Act: 2.3354. Min Act: -0.0001
Data Index: 17904 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19