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

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

Neuron 4889 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1990. Min Range: -2.1990

Max Act: 2.1990. Min Act: -0.0000

Data Index: 756493 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.8547. Min Act: -0.0000

Data Index: 95587 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.9176. Min Act: -0.0000

Data Index: 564136 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 2.1990. Min Range: -2.1990

Max Act: 2.1186. Min Act: -0.0000

Data Index: 1335444 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.9353. Min Act: -0.0000

Data Index: 866199 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.9073. Min Act: -0.0000

Data Index: 712821 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.7232. Min Act: -0.0000

Data Index: 848933 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6981. Min Act: 0.0000

Data Index: 285368 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6908. Min Act: -0.0000

Data Index: 844107 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6707. Min Act: -0.0000

Data Index: 674514 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.7427. Min Act: -0.0000

Data Index: 645080 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.7451. Min Act: -0.0000

Data Index: 593874 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.8298. Min Act: -0.0000

Data Index: 56536 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.5121. Min Act: -0.0000

Data Index: 1295657 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6724. Min Act: -0.0000

Data Index: 316537 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1271175 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.5800. Min Act: -0.0000

Data Index: 814397 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6489. Min Act: -0.0000

Data Index: 774071 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6265. Min Act: -0.0000

Data Index: 1191238 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1047944 (C4 (Web Text))

Max Activating Token Index: 730