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

Dataset: The Pile

Neuron 71 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: 0.2762. Min Range: -0.2762

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1321479 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1164226 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2602. Min Act: -0.0000

Data Index: 471153 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1121793 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2537. Min Act: -0.0000

Data Index: 273516 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2676. Min Act: -0.0000

Data Index: 505434 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1273944 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1319433 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2488. Min Act: -0.0000

Data Index: 403256 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1318514 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1971821 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2385. Min Act: -0.0000

Data Index: 2473 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2441. Min Act: -0.0000

Data Index: 898846 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1555366 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1883101 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2342. Min Act: -0.0000

Data Index: 603478 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1126479 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1930812 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1614936 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.2762. Min Range: -0.2762

Max Act: 0.2128. Min Act: -0.0000

Data Index: 958552 (The Pile)

Max Activating Token Index: 615