Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0758. Min Range: -1.0758

Max Act: 1.0690. Min Act: -0.0001

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.0758. Min Range: -1.0758

Max Act: 1.0758. Min Act: -0.0001

Data Index: 565995 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9663. Min Act: -0.0000

Data Index: 635655 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1082435 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9511. Min Act: -0.0000

Data Index: 165744 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8676. Min Act: -0.0000

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8967. Min Act: -0.0001

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9036. Min Act: -0.0000

Data Index: 771812 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7582. Min Act: -0.0001

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8241. Min Act: -0.0001

Data Index: 137223 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7505. Min Act: -0.0000

Data Index: 303392 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8094. Min Act: -0.0000

Data Index: 424903 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7742. Min Act: -0.0000

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7896. Min Act: -0.0000

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7565. Min Act: -0.0000

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7268. Min Act: -0.0001

Data Index: 954444 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7773. Min Act: -0.0000

Data Index: 927942 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7133. Min Act: -0.0000

Data Index: 637459 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7399. Min Act: -0.0000

Data Index: 161291 (C4 (Web Text))

Max Activating Token Index: 482