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

Dataset: The Pile

Neuron 2636 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1988128 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1497601 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1781224 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.5323. Min Act: -0.0000

Data Index: 698598 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1627271 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1854061 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.5147. Min Act: -0.0000

Data Index: 858627 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4298. Min Act: -0.0000

Data Index: 478411 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4447. Min Act: -0.0000

Data Index: 464190 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4556. Min Act: -0.0000

Data Index: 249596 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1866698 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.3722. Min Act: -0.0001

Data Index: 962431 (The Pile)

Max Activating Token Index: 909

Text #12

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1936409 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4277. Min Act: -0.0000

Data Index: 494290 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1423705 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4060. Min Act: -0.0000

Data Index: 553135 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4456. Min Act: -0.0000

Data Index: 517973 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.3528. Min Act: -0.0000

Data Index: 103569 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.3823. Min Act: -0.0000

Data Index: 257 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.5614. Min Range: -0.5614

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1505783 (The Pile)

Max Activating Token Index: 651