Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 201 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0006

Data Index: 1012834 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0328. Min Act: -0.0006

Data Index: 666325 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1202394 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0285. Min Act: -0.0006

Data Index: 695524 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0266. Min Act: -0.0006

Data Index: 30035 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0290. Min Act: -0.0006

Data Index: 292856 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0261. Min Act: -0.0006

Data Index: 48733 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0269. Min Act: -0.0006

Data Index: 88444 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0249. Min Act: -0.0006

Data Index: 754705 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1166556 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1151184 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0241. Min Act: -0.0006

Data Index: 964818 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0261. Min Act: -0.0006

Data Index: 1056442 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0255. Min Act: -0.0006

Data Index: 209709 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0261. Min Act: -0.0006

Data Index: 465378 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1226604 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0249. Min Act: -0.0006

Data Index: 408054 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0242. Min Act: -0.0006

Data Index: 949350 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0251. Min Act: -0.0006

Data Index: 512344 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0237. Min Act: -0.0006

Data Index: 463096 (C4 (Web Text))

Max Activating Token Index: 513