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

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

Neuron 736 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: 0.9355. Min Range: -0.9355

Max Act: 0.9253. Min Act: -0.0000

Data Index: 299491 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1227137 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.9355. Min Act: -0.0000

Data Index: 639523 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7719. Min Act: -0.0000

Data Index: 319762 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.8350. Min Act: -0.0000

Data Index: 323702 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.8276. Min Act: -0.0000

Data Index: 555120 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1049060 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7522. Min Act: -0.0000

Data Index: 123054 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7120. Min Act: -0.0000

Data Index: 301726 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1226400 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7032. Min Act: -0.0000

Data Index: 467988 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7124. Min Act: -0.0000

Data Index: 922063 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.6670. Min Act: -0.0000

Data Index: 957717 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.6685. Min Act: -0.0000

Data Index: 393891 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1271427 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.6644. Min Act: -0.0000

Data Index: 430223 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.7338. Min Act: -0.0000

Data Index: 851163 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.6379. Min Act: -0.0000

Data Index: 322607 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.6968. Min Act: -0.0000

Data Index: 902779 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.9355. Min Range: -0.9355

Max Act: 0.6542. Min Act: -0.0000

Data Index: 146738 (C4 (Web Text))

Max Activating Token Index: 656