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

Dataset: The Pile

Neuron 4655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7498. Min Act: -0.0000

Data Index: 498954 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7023. Min Act: -0.0000

Data Index: 131720 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1690958 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1393959 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6785. Min Act: -0.0000

Data Index: 150247 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1841210 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1148127 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1008291 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6033. Min Act: -0.0000

Data Index: 312237 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1186407 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5816. Min Act: -0.0000

Data Index: 38681 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1242785 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5829. Min Act: -0.0000

Data Index: 774634 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1472479 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1244428 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5541. Min Act: -0.0000

Data Index: 414251 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5560. Min Act: -0.0000

Data Index: 281281 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1705437 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5481. Min Act: -0.0000

Data Index: 819037 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5186. Min Act: -0.0000

Data Index: 197956 (The Pile)

Max Activating Token Index: 184