Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5102 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2143. Min Range: -5.2143

Max Act: 5.2143. Min Act: -0.0001

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 5.2143. Min Range: -5.2143

Max Act: 5.1690. Min Act: -0.0000

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 5.2143. Min Range: -5.2143

Max Act: 5.1143. Min Act: -0.0000

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.9243. Min Act: -0.0001

Data Index: 493994 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6677. Min Act: -0.0000

Data Index: 228091 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8271. Min Act: -0.0000

Data Index: 671486 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.9309. Min Act: -0.0001

Data Index: 698786 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.9334. Min Act: -0.0001

Data Index: 80468 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.7332. Min Act: -0.0000

Data Index: 559083 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 5.2143. Min Range: -5.2143

Max Act: 5.0464. Min Act: -0.0000

Data Index: 961421 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6713. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6673. Min Act: -0.0000

Data Index: 1289001 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8023. Min Act: -0.0001

Data Index: 486726 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.4942. Min Act: -0.0000

Data Index: 596507 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8167. Min Act: -0.0001

Data Index: 1327575 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.4865. Min Act: -0.0000

Data Index: 117533 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.9571. Min Act: -0.0000

Data Index: 1354218 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8099. Min Act: -0.0000

Data Index: 325940 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8793. Min Act: -0.0000

Data Index: 1204296 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6712. Min Act: -0.0001

Data Index: 488097 (C4 (Web Text))

Max Activating Token Index: 762