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

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

Neuron 2087 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0899. Min Range: -1.0899

Max Act: 1.0899. Min Act: -0.0001

Data Index: 700761 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9882. Min Act: -0.0001

Data Index: 407378 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9523. Min Act: -0.0001

Data Index: 1284263 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 1.0899. Min Range: -1.0899

Max Act: 1.0204. Min Act: -0.0001

Data Index: 828495 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.9580. Min Act: -0.0001

Data Index: 231036 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8866. Min Act: -0.0001

Data Index: 237421 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8258. Min Act: -0.0001

Data Index: 824889 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1011636 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8829. Min Act: -0.0001

Data Index: 9946 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8448. Min Act: -0.0001

Data Index: 875107 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7412. Min Act: -0.0001

Data Index: 781077 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.8222. Min Act: -0.0001

Data Index: 529138 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7385. Min Act: -0.0001

Data Index: 193834 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7449. Min Act: -0.0001

Data Index: 217964 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1231961 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7675. Min Act: -0.0001

Data Index: 376156 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7323. Min Act: -0.0001

Data Index: 860099 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1026976 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7292. Min Act: -0.0001

Data Index: 590052 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.0899. Min Range: -1.0899

Max Act: 0.7706. Min Act: -0.0001

Data Index: 267323 (C4 (Web Text))

Max Activating Token Index: 24