Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.4938. Min Act: -0.0000

Data Index: 1415451 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.6165. Min Act: -0.0000

Data Index: 1461833 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3339. Min Act: -0.0000

Data Index: 136277 (The Pile)

Max Activating Token Index: 619

Text #3

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2752. Min Act: 0.0000

Data Index: 47891 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3713. Min Act: -0.0000

Data Index: 628892 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3724. Min Act: -0.0000

Data Index: 1665922 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.5247. Min Act: -0.0000

Data Index: 332394 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2972. Min Act: 0.0000

Data Index: 1387777 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1097415 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3699. Min Act: -0.0000

Data Index: 475142 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1442622 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1216314 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.1996. Min Act: -0.0000

Data Index: 182967 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3871. Min Act: -0.0000

Data Index: 293765 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2492. Min Act: -0.0000

Data Index: 708586 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2979. Min Act: -0.0000

Data Index: 1016909 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2129. Min Act: -0.0000

Data Index: 989935 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1482926 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.1857. Min Act: -0.0000

Data Index: 278029 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1527376 (The Pile)

Max Activating Token Index: 700