Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1438 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4933. Min Act: -0.0000

Data Index: 594006 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4669. Min Act: -0.0000

Data Index: 863004 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1871086 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1872586 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3426. Min Act: -0.0000

Data Index: 796844 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2739. Min Act: -0.0000

Data Index: 164145 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2718. Min Act: -0.0000

Data Index: 251628 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2805. Min Act: -0.0000

Data Index: 899534 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2723. Min Act: -0.0000

Data Index: 158314 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2506. Min Act: -0.0000

Data Index: 518511 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2406. Min Act: -0.0000

Data Index: 895494 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1538847 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2469. Min Act: -0.0000

Data Index: 778490 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2403. Min Act: -0.0000

Data Index: 37513 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2402. Min Act: -0.0000

Data Index: 130630 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1065664 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1470901 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2178. Min Act: -0.0000

Data Index: 41944 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1828516 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.2309. Min Act: -0.0000

Data Index: 367023 (The Pile)

Max Activating Token Index: 846