Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2016 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0366. Min Act: -0.0001
Data Index: 1014886 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0350. Min Act: -0.0001
Data Index: 190285 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0331. Min Act: -0.0001
Data Index: 1170028 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0341. Min Act: -0.0001
Data Index: 556025 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0277. Min Act: -0.0001
Data Index: 876956 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0272. Min Act: -0.0001
Data Index: 1165564 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0267. Min Act: -0.0001
Data Index: 1225001 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0261. Min Act: -0.0001
Data Index: 1023938 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0261. Min Act: -0.0001
Data Index: 753639 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0262. Min Act: -0.0001
Data Index: 1085054 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0242. Min Act: -0.0001
Data Index: 953352 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0259. Min Act: -0.0001
Data Index: 1547063 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0254. Min Act: -0.0001
Data Index: 448428 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0275. Min Act: -0.0001
Data Index: 584578 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0253. Min Act: -0.0001
Data Index: 634559 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0246. Min Act: -0.0001
Data Index: 1158103 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0235. Min Act: -0.0001
Data Index: 469713 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0252. Min Act: -0.0001
Data Index: 1277301 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0252. Min Act: -0.0001
Data Index: 604186 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0366. Min Range: -0.0366
Max Act: 0.0248. Min Act: -0.0001
Data Index: 1280165 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19