Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 33 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1020853 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0211. Min Act: -0.0006

Data Index: 388225 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0201. Min Act: -0.0006

Data Index: 375688 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1179680 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0181. Min Act: -0.0006

Data Index: 684796 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0189. Min Act: -0.0006

Data Index: 453980 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0006

Data Index: 950045 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0006

Data Index: 980824 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0185. Min Act: -0.0006

Data Index: 94263 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0192. Min Act: -0.0006

Data Index: 482921 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1040468 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0006

Data Index: 241608 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0178. Min Act: -0.0006

Data Index: 728245 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0006

Data Index: 128706 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1305394 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0192. Min Act: -0.0006

Data Index: 115023 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0183. Min Act: -0.0006

Data Index: 666730 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0183. Min Act: -0.0006

Data Index: 147892 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0006

Data Index: 411646 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0006

Data Index: 61848 (C4 (Web Text))

Max Activating Token Index: 13