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

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

Neuron 1648 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: 2.2464. Min Range: -2.2464

Max Act: 2.2464. Min Act: -0.0000

Data Index: 1198067 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 2.2464. Min Range: -2.2464

Max Act: 2.1182. Min Act: -0.0000

Data Index: 199618 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.6183. Min Act: -0.0000

Data Index: 405963 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.6518. Min Act: -0.0000

Data Index: 1055243 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.6705. Min Act: -0.0000

Data Index: 1115167 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.6677. Min Act: -0.0000

Data Index: 1172756 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.6771. Min Act: -0.0000

Data Index: 188028 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.6222. Min Act: -0.0000

Data Index: 319236 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.6113. Min Act: -0.0000

Data Index: 452177 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5788. Min Act: -0.0000

Data Index: 687235 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5726. Min Act: -0.0000

Data Index: 917111 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1206125 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5249. Min Act: -0.0000

Data Index: 245316 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1149671 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1186026 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5141. Min Act: -0.0000

Data Index: 425321 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.4631. Min Act: -0.0000

Data Index: 105806 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.4877. Min Act: -0.0000

Data Index: 124132 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.4357. Min Act: -0.0000

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 2.2464. Min Range: -2.2464

Max Act: 1.5669. Min Act: -0.0000

Data Index: 604417 (C4 (Web Text))

Max Activating Token Index: 737