Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3140 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2477. Min Act: -0.0000

Data Index: 563527 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2480. Min Act: -0.0000

Data Index: 692352 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2367. Min Act: -0.0000

Data Index: 170468 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2294. Min Act: -0.0000

Data Index: 426410 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2168. Min Act: -0.0000

Data Index: 969866 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2149. Min Act: -0.0000

Data Index: 224606 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2212. Min Act: -0.0000

Data Index: 323831 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2014. Min Act: -0.0000

Data Index: 393094 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2088. Min Act: -0.0000

Data Index: 266128 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2047. Min Act: -0.0000

Data Index: 512089 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2032. Min Act: -0.0000

Data Index: 201556 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1057321 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1985. Min Act: -0.0000

Data Index: 268172 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1119618 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1905. Min Act: -0.0000

Data Index: 362314 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1954. Min Act: -0.0000

Data Index: 374498 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1934. Min Act: -0.0000

Data Index: 878127 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1898. Min Act: -0.0000

Data Index: 880122 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1314181 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1900. Min Act: -0.0000

Data Index: 597997 (C4 (Web Text))

Max Activating Token Index: 945