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

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

Neuron 627 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.7975. Min Act: -0.0000

Data Index: 1248484 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.2959. Min Act: -0.0000

Data Index: 260203 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.4536. Min Act: -0.0000

Data Index: 1273025 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.3066. Min Act: -0.0000

Data Index: 1198840 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.1716. Min Act: -0.0000

Data Index: 864217 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.3126. Min Act: -0.0000

Data Index: 58517 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.9149. Min Act: -0.0000

Data Index: 794578 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.9909. Min Act: -0.0000

Data Index: 863188 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.1768. Min Act: -0.0000

Data Index: 718475 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 2.7975. Min Range: -2.7975

Max Act: 2.1877. Min Act: -0.0000

Data Index: 1152776 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.9937. Min Act: -0.0000

Data Index: 732676 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.9784. Min Act: -0.0000

Data Index: 616158 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.8535. Min Act: -0.0000

Data Index: 467378 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.8478. Min Act: -0.0000

Data Index: 712210 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.8220. Min Act: -0.0000

Data Index: 747745 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.8393. Min Act: -0.0000

Data Index: 254120 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.8335. Min Act: -0.0000

Data Index: 343302 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1553245 (Python Code)

Max Activating Token Index: 667

Text #18

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.8188. Min Act: -0.0000

Data Index: 614959 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.7975. Min Range: -2.7975

Max Act: 1.5144. Min Act: -0.0000

Data Index: 425191 (C4 (Web Text))

Max Activating Token Index: 848