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

Dataset: The Pile

Neuron 3579 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: 1.9385. Min Range: -1.9385

Max Act: 1.9385. Min Act: -0.0000

Data Index: 486941 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1808043 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4440. Min Act: -0.0000

Data Index: 241014 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.3522. Min Act: -0.0000

Data Index: 220654 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4227. Min Act: -0.0000

Data Index: 1060801 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.3648. Min Act: -0.0000

Data Index: 954985 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1559018 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.3795. Min Act: -0.0000

Data Index: 912758 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1118123 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.1657. Min Act: -0.0000

Data Index: 17554 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.3091. Min Act: -0.0000

Data Index: 644013 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.2278. Min Act: -0.0000

Data Index: 20576 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1872326 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1729928 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1611455 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1635247 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.1952. Min Act: -0.0000

Data Index: 136331 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1542788 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1542058 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.1427. Min Act: -0.0000

Data Index: 779334 (The Pile)

Max Activating Token Index: 760