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

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

Neuron 3983 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2784. Min Act: -0.0000

Data Index: 457834 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2661. Min Act: -0.0000

Data Index: 537784 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2724. Min Act: -0.0000

Data Index: 100700 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2485. Min Act: -0.0000

Data Index: 1409492 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1206187 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2529. Min Act: -0.0000

Data Index: 221272 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2528. Min Act: -0.0000

Data Index: 337225 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2352. Min Act: -0.0000

Data Index: 114203 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2330. Min Act: -0.0000

Data Index: 458589 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2324. Min Act: -0.0000

Data Index: 366914 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2258. Min Act: -0.0000

Data Index: 431925 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2296. Min Act: -0.0000

Data Index: 270521 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2156. Min Act: -0.0000

Data Index: 142360 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2206. Min Act: -0.0000

Data Index: 259100 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2115. Min Act: -0.0000

Data Index: 646446 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2231. Min Act: -0.0000

Data Index: 334358 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2159. Min Act: -0.0000

Data Index: 84249 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2164. Min Act: -0.0000

Data Index: 613537 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2234. Min Act: -0.0000

Data Index: 623962 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.2784. Min Range: -0.2784

Max Act: 0.2143. Min Act: -0.0000

Data Index: 988097 (C4 (Web Text))

Max Activating Token Index: 254