Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 433 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1151796 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.0297. Min Range: -1.0297

Max Act: 1.0297. Min Act: -0.0001

Data Index: 291181 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.9220. Min Act: -0.0001

Data Index: 902679 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8866. Min Act: -0.0001

Data Index: 100671 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8926. Min Act: -0.0001

Data Index: 326552 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8604. Min Act: -0.0001

Data Index: 758234 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8279. Min Act: -0.0001

Data Index: 536926 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8171. Min Act: -0.0001

Data Index: 804661 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7862. Min Act: -0.0001

Data Index: 153511 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7411. Min Act: -0.0001

Data Index: 303731 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1316456 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1106988 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8761. Min Act: -0.0001

Data Index: 595509 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8087. Min Act: -0.0001

Data Index: 505848 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7787. Min Act: -0.0001

Data Index: 110186 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.6873. Min Act: -0.0001

Data Index: 898918 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.9396. Min Act: -0.0001

Data Index: 1345890 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.7946. Min Act: -0.0001

Data Index: 65544 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8200. Min Act: -0.0001

Data Index: 137574 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.0297. Min Range: -1.0297

Max Act: 0.8662. Min Act: -0.0001

Data Index: 251038 (C4 (Web Text))

Max Activating Token Index: 681