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

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

Neuron 4578 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8413. Min Act: -0.0000

Data Index: 664887 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8970. Min Act: -0.0000

Data Index: 523538 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8596. Min Act: -0.0000

Data Index: 591394 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8378. Min Act: -0.0000

Data Index: 674539 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1286026 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1120183 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1248397 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8300. Min Act: -0.0000

Data Index: 367883 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7663. Min Act: -0.0000

Data Index: 728536 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8437. Min Act: -0.0000

Data Index: 938316 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8085. Min Act: -0.0000

Data Index: 614171 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8200. Min Act: -0.0000

Data Index: 252784 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7639. Min Act: -0.0000

Data Index: 295904 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1008969 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7553. Min Act: -0.0000

Data Index: 116981 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1101514 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1256225 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6879. Min Act: -0.0000

Data Index: 691623 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7211. Min Act: -0.0000

Data Index: 116479 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7161. Min Act: -0.0000

Data Index: 338818 (C4 (Web Text))

Max Activating Token Index: 150