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

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

Neuron 5894 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.8576. Min Act: -0.0000

Data Index: 463479 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.8975. Min Act: -0.0000

Data Index: 934195 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.9160. Min Act: -0.0000

Data Index: 831068 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.6282. Min Act: -0.0000

Data Index: 969099 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.6747. Min Act: -0.0000

Data Index: 829955 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.4890. Min Act: -0.0000

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.4771. Min Act: -0.0000

Data Index: 256281 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.4407. Min Act: -0.0000

Data Index: 1184876 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.3165. Min Act: -0.0000

Data Index: 1055156 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.1937. Min Act: -0.0000

Data Index: 891997 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.3948. Min Act: -0.0000

Data Index: 1203880 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.2548. Min Act: -0.0000

Data Index: 631592 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.2380. Min Act: -0.0000

Data Index: 1202074 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.3614. Min Act: -0.0000

Data Index: 370144 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.3413. Min Act: -0.0000

Data Index: 115898 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.1132. Min Act: -0.0000

Data Index: 569531 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.2429. Min Act: -0.0000

Data Index: 1219194 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.1772. Min Act: -0.0000

Data Index: 283525 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.1431. Min Act: -0.0000

Data Index: 1110743 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 2.9160. Min Range: -2.9160

Max Act: 2.2350. Min Act: -0.0000

Data Index: 359288 (C4 (Web Text))

Max Activating Token Index: 310