Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2940. Min Act: -0.0000

Data Index: 972902 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1371557 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2574. Min Act: -0.0000

Data Index: 171405 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1942354 (The Pile)

Max Activating Token Index: 8

Text #4

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1786637 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1926292 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2362. Min Act: -0.0000

Data Index: 728051 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2334. Min Act: -0.0000

Data Index: 737183 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2305. Min Act: -0.0000

Data Index: 162022 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2374. Min Act: -0.0000

Data Index: 530944 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1102627 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1566673 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1496222 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2270. Min Act: -0.0000

Data Index: 671658 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1161315 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1377491 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1539156 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1279343 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1625610 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2193. Min Act: -0.0000

Data Index: 405656 (The Pile)

Max Activating Token Index: 39