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

Dataset: The Pile

Neuron 1234 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: 1.6280. Min Range: -1.6280

Max Act: 1.6280. Min Act: -0.0000

Data Index: 919478 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 1.6280. Min Range: -1.6280

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1947409 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 1.6280. Min Range: -1.6280

Max Act: 1.1060. Min Act: -0.0000

Data Index: 731155 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 1.6280. Min Range: -1.6280

Max Act: 1.0520. Min Act: -0.0000

Data Index: 402864 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1147650 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1690508 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1123929 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.9229. Min Act: 0.0000

Data Index: 1336367 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8424. Min Act: 0.0000

Data Index: 998652 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1729161 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.9336. Min Act: -0.0000

Data Index: 552001 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8990. Min Act: -0.0000

Data Index: 335412 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1905821 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1457767 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8221. Min Act: -0.0000

Data Index: 389597 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1532555 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8664. Min Act: -0.0000

Data Index: 619393 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8845. Min Act: -0.0000

Data Index: 711203 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8618. Min Act: -0.0000

Data Index: 636425 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 1.6280. Min Range: -1.6280

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1650691 (The Pile)

Max Activating Token Index: 206