Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3244 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.6244. Min Act: -0.0000

Data Index: 1216304 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.6197. Min Act: -0.0000

Data Index: 210607 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.7282. Min Act: -0.0000

Data Index: 894798 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.6786. Min Act: -0.0000

Data Index: 1145212 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.5214. Min Act: -0.0000

Data Index: 562274 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.4115. Min Act: -0.0000

Data Index: 728495 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.5605. Min Act: -0.0000

Data Index: 333155 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.5991. Min Act: -0.0000

Data Index: 1062836 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.5699. Min Act: -0.0000

Data Index: 1190681 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.3510. Min Act: -0.0000

Data Index: 662036 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.3279. Min Act: -0.0000

Data Index: 14459 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.5694. Min Act: -0.0000

Data Index: 197559 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.3076. Min Act: -0.0000

Data Index: 198334 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.2794. Min Act: -0.0000

Data Index: 920366 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.5319. Min Act: -0.0000

Data Index: 295465 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.1503. Min Act: -0.0000

Data Index: 42077 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.1238. Min Act: -0.0000

Data Index: 236327 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.2173. Min Act: -0.0000

Data Index: 613378 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.2128. Min Act: -0.0000

Data Index: 418102 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 2.7282. Min Range: -2.7282

Max Act: 2.0997. Min Act: -0.0000

Data Index: 184249 (C4 (Web Text))

Max Activating Token Index: 536