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

Dataset: The Pile

Neuron 4016 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: 0.3442. Min Range: -0.3442

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1500232 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2943. Min Act: -0.0000

Data Index: 178700 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3286. Min Act: -0.0000

Data Index: 645646 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3442. Min Act: 0.0000

Data Index: 510337 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.3091. Min Act: 0.0000

Data Index: 1299920 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1727601 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1610868 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2914. Min Act: -0.0000

Data Index: 727035 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1122471 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1968670 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1606478 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2613. Min Act: -0.0000

Data Index: 781899 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2542. Min Act: 0.0000

Data Index: 164906 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2263. Min Act: -0.0000

Data Index: 665862 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2478. Min Act: -0.0000

Data Index: 686716 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1552200 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2485. Min Act: -0.0000

Data Index: 108257 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1029653 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2481. Min Act: 0.0000

Data Index: 120420 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 0.3442. Min Range: -0.3442

Max Act: 0.2304. Min Act: -0.0000

Data Index: 175243 (The Pile)

Max Activating Token Index: 146