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

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

Neuron 1999 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2560. Min Act: -0.0002

Data Index: 414980 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2466. Min Act: -0.0002

Data Index: 155821 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2453. Min Act: -0.0002

Data Index: 1165690 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2255. Min Act: -0.0002

Data Index: 178399 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2282. Min Act: -0.0002

Data Index: 508109 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2275. Min Act: -0.0001

Data Index: 599220 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2164. Min Act: -0.0002

Data Index: 682310 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2148. Min Act: -0.0002

Data Index: 397975 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2183. Min Act: -0.0002

Data Index: 223475 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2100. Min Act: -0.0002

Data Index: 760810 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2175. Min Act: -0.0002

Data Index: 352231 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2173. Min Act: -0.0002

Data Index: 148033 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2006. Min Act: -0.0002

Data Index: 249092 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2208. Min Act: -0.0002

Data Index: 613045 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2133. Min Act: -0.0002

Data Index: 1148109 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2134. Min Act: -0.0001

Data Index: 869087 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2120. Min Act: -0.0002

Data Index: 74632 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2137. Min Act: -0.0002

Data Index: 618186 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2038. Min Act: -0.0002

Data Index: 403517 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2027. Min Act: -0.0002

Data Index: 1273916 (C4 (Web Text))

Max Activating Token Index: 282