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

Dataset: The Pile

Neuron 2493 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4495. Min Act: 0.0000

Data Index: 269553 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4468. Min Act: 0.0000

Data Index: 1046026 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1293519 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1013735 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1534033 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1302277 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1352238 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3429. Min Act: -0.0000

Data Index: 394971 (The Pile)

Max Activating Token Index: 491

Text #8

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3348. Min Act: -0.0000

Data Index: 51269 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1553352 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3036. Min Act: -0.0000

Data Index: 566262 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1286639 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3257. Min Act: -0.0000

Data Index: 262607 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3011. Min Act: -0.0000

Data Index: 640995 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1838210 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1378926 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1400697 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1926189 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2974. Min Act: 0.0000

Data Index: 1898860 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2940. Min Act: -0.0000

Data Index: 79339 (The Pile)

Max Activating Token Index: 954