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

Dataset: The Pile

Neuron 3566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3509. Min Act: -0.0000

Data Index: 227363 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1642844 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2479. Min Act: -0.0000

Data Index: 990480 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1989014 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1004661 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1760279 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1992558 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2461. Min Act: -0.0000

Data Index: 114076 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1226318 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1780056 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2505. Min Act: -0.0000

Data Index: 254318 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1834224 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1686190 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2428. Min Act: -0.0000

Data Index: 406957 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1073264 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2415. Min Act: -0.0000

Data Index: 33341 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2417. Min Act: -0.0000

Data Index: 174626 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1159115 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1700975 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1558870 (The Pile)

Max Activating Token Index: 58