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

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

Neuron 3943 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8731. Min Act: -0.0000

Data Index: 803435 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8182. Min Act: -0.0000

Data Index: 404155 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1422136 (Python Code)

Max Activating Token Index: 295

Text #3

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1412215 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1175991 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1124728 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7487. Min Act: -0.0000

Data Index: 903323 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7912. Min Act: -0.0000

Data Index: 989062 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7636. Min Act: -0.0000

Data Index: 683224 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8088. Min Act: -0.0000

Data Index: 330449 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6637. Min Act: -0.0000

Data Index: 35840 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1529055 (Python Code)

Max Activating Token Index: 285

Text #12

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7463. Min Act: -0.0000

Data Index: 651988 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7455. Min Act: -0.0000

Data Index: 146329 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1012223 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1482359 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1105163 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6219. Min Act: -0.0000

Data Index: 576914 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1329652 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1300749 (C4 (Web Text))

Max Activating Token Index: 47