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

Dataset: The Pile

Neuron 807 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6448. Min Act: -0.0000

Data Index: 18598 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.7400. Min Act: -0.0000

Data Index: 1273635 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.4427. Min Act: -0.0000

Data Index: 681036 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.4249. Min Act: -0.0000

Data Index: 325647 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.4502. Min Act: -0.0000

Data Index: 785976 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.3549. Min Act: -0.0000

Data Index: 100042 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1495823 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1763033 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1543365 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1309331 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2929. Min Act: -0.0000

Data Index: 481840 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2938. Min Act: -0.0000

Data Index: 292432 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1550458 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1966050 (The Pile)

Max Activating Token Index: 303

Text #14

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.1866. Min Act: -0.0000

Data Index: 650570 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1635490 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.3447. Min Act: -0.0000

Data Index: 643864 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2021. Min Act: -0.0000

Data Index: 795616 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2098. Min Act: -0.0000

Data Index: 828556 (The Pile)

Max Activating Token Index: 267

Text #19

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1926803 (The Pile)

Max Activating Token Index: 221