Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3301 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0310. Min Act: -0.0002
Data Index: 265031 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0294. Min Act: -0.0002
Data Index: 1277277 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0274. Min Act: -0.0002
Data Index: 1416021 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0265. Min Act: -0.0002
Data Index: 73335 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0252. Min Act: -0.0002
Data Index: 1580280 (Python Code)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0246. Min Act: -0.0002
Data Index: 489308 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0243. Min Act: -0.0002
Data Index: 1362315 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0241. Min Act: -0.0002
Data Index: 212605 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0237. Min Act: -0.0002
Data Index: 187298 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0225. Min Act: -0.0002
Data Index: 222938 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0219. Min Act: -0.0002
Data Index: 984407 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0218. Min Act: -0.0002
Data Index: 313622 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0218. Min Act: -0.0002
Data Index: 1532905 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0215. Min Act: -0.0001
Data Index: 662362 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0211. Min Act: -0.0002
Data Index: 1269886 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0211. Min Act: -0.0002
Data Index: 1573284 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0209. Min Act: -0.0002
Data Index: 242083 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0209. Min Act: -0.0002
Data Index: 648527 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0209. Min Act: -0.0002
Data Index: 196566 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0310. Min Range: -0.0310
Max Act: 0.0207. Min Act: -0.0002
Data Index: 947598 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19