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

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

Neuron 3218 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2358. Min Range: -1.2358

Max Act: 1.2358. Min Act: -0.0000

Data Index: 496264 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 1.2358. Min Range: -1.2358

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1009053 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.9074. Min Act: -0.0000

Data Index: 458472 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.8878. Min Act: -0.0000

Data Index: 921542 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.9082. Min Act: -0.0000

Data Index: 405628 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.8366. Min Act: -0.0000

Data Index: 378661 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.8180. Min Act: -0.0000

Data Index: 49786 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7883. Min Act: -0.0000

Data Index: 650534 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1343481 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1446520 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7347. Min Act: -0.0000

Data Index: 673603 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7814. Min Act: -0.0000

Data Index: 965009 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1043235 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7685. Min Act: -0.0000

Data Index: 815240 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7304. Min Act: -0.0000

Data Index: 870174 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7564. Min Act: -0.0000

Data Index: 311164 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7439. Min Act: -0.0000

Data Index: 149652 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1253758 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.7094. Min Act: -0.0000

Data Index: 375080 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.2358. Min Range: -1.2358

Max Act: 0.6832. Min Act: -0.0000

Data Index: 508702 (C4 (Web Text))

Max Activating Token Index: 708