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

Dataset: The Pile

Neuron 724 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6373. Min Act: -0.0000

Data Index: 478169 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1457316 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1607140 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5496. Min Act: -0.0000

Data Index: 742645 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1856100 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4639. Min Act: -0.0000

Data Index: 563584 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1053088 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1902299 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1125430 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1605243 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4704. Min Act: -0.0000

Data Index: 447301 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1541181 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4534. Min Act: -0.0000

Data Index: 24656 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1062877 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1188361 (The Pile)

Max Activating Token Index: 300

Text #15

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4364. Min Act: -0.0000

Data Index: 542628 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4422. Min Act: -0.0000

Data Index: 930980 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1223906 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4361. Min Act: -0.0000

Data Index: 623618 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1983177 (The Pile)

Max Activating Token Index: 974