Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2924 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6494. Min Act: 0.0000

Data Index: 1566357 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6226. Min Act: 0.0001

Data Index: 1342887 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5773. Min Act: 0.0001

Data Index: 1162335 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5531. Min Act: 0.0001

Data Index: 1480188 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5448. Min Act: 0.0000

Data Index: 1524114 (Python Code)

Max Activating Token Index: 483

Text #5

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1355245 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5252. Min Act: -0.0000

Data Index: 746580 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4838. Min Act: 0.0001

Data Index: 1606063 (Python Code)

Max Activating Token Index: 443

Text #8

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4925. Min Act: -0.0000

Data Index: 617513 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4943. Min Act: -0.0000

Data Index: 731533 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4874. Min Act: 0.0000

Data Index: 89440 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4771. Min Act: 0.0001

Data Index: 1652555 (Python Code)

Max Activating Token Index: 838

Text #12

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1350440 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4613. Min Act: 0.0001

Data Index: 1319037 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1589816 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4568. Min Act: 0.0000

Data Index: 1549942 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4885. Min Act: 0.0001

Data Index: 283520 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4757. Min Act: -0.0000

Data Index: 842242 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1625740 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4711. Min Act: 0.0001

Data Index: 718353 (C4 (Web Text))

Max Activating Token Index: 500