Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 245 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.4257. Min Act: -0.0001
Data Index: 662258 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.3243. Min Act: -0.0001
Data Index: 489170 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1513. Min Act: -0.0001
Data Index: 862567 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.0881. Min Act: -0.0001
Data Index: 565317 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1280. Min Act: -0.0001
Data Index: 19424 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1011. Min Act: -0.0001
Data Index: 1158304 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1616. Min Act: -0.0001
Data Index: 583270 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.0806. Min Act: -0.0001
Data Index: 769484 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1628. Min Act: -0.0001
Data Index: 1203253 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1320. Min Act: -0.0001
Data Index: 321146 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1810. Min Act: -0.0001
Data Index: 842335 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1370. Min Act: -0.0001
Data Index: 731265 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1262. Min Act: -0.0001
Data Index: 333492 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1486. Min Act: -0.0001
Data Index: 1229355 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.0860. Min Act: -0.0001
Data Index: 724772 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.0860. Min Act: -0.0001
Data Index: 137450 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.1141. Min Act: -0.0001
Data Index: 1177178 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.0692. Min Act: -0.0001
Data Index: 1217818 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.0862. Min Act: -0.0001
Data Index: 1175885 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4257. Min Range: -1.4257
Max Act: 1.0353. Min Act: -0.0001
Data Index: 187307 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19