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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4364 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.5743. Min Act: -0.0000

Data Index: 873564 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.5310. Min Act: -0.0000

Data Index: 420536 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.5225. Min Act: -0.0000

Data Index: 87449 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.5121. Min Act: -0.0000

Data Index: 326688 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4215. Min Act: -0.0000

Data Index: 889901 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4186. Min Act: -0.0000

Data Index: 583071 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4098. Min Act: -0.0000

Data Index: 260374 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1336609 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4061. Min Act: -0.0000

Data Index: 827114 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3956. Min Act: -0.0000

Data Index: 695408 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1154925 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3808. Min Act: -0.0000

Data Index: 105227 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4054. Min Act: -0.0000

Data Index: 555224 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1132063 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3872. Min Act: -0.0000

Data Index: 188568 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3653. Min Act: -0.0000

Data Index: 244802 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.4042. Min Act: -0.0000

Data Index: 617069 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3520. Min Act: -0.0000

Data Index: 435866 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3671. Min Act: -0.0000

Data Index: 300971 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.5743. Min Range: -0.5743

Max Act: 0.3571. Min Act: -0.0000

Data Index: 420790 (C4 (Web Text))

Max Activating Token Index: 251