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

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

Neuron 2679 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.2143. Min Act: -0.0001

Data Index: 1028770 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1048. Min Act: -0.0000

Data Index: 527706 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0609. Min Act: -0.0000

Data Index: 246090 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.9045. Min Act: -0.0000

Data Index: 213183 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1165. Min Act: -0.0000

Data Index: 859571 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.2457. Min Act: -0.0001

Data Index: 874385 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.7894. Min Act: -0.0001

Data Index: 873598 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.6153. Min Act: -0.0001

Data Index: 167901 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.7078. Min Act: -0.0000

Data Index: 1128415 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.4989. Min Act: -0.0000

Data Index: 771051 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.6038. Min Act: -0.0001

Data Index: 410440 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.4815. Min Act: -0.0000

Data Index: 343031 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.5942. Min Act: -0.0000

Data Index: 410362 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.5181. Min Act: -0.0000

Data Index: 1206242 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.4751. Min Act: -0.0000

Data Index: 1262756 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.4827. Min Act: -0.0000

Data Index: 20485 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.4513. Min Act: -0.0001

Data Index: 1227894 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.3249. Min Act: -0.0000

Data Index: 1065112 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.1867. Min Act: -0.0000

Data Index: 479713 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.2457. Min Range: -3.2457

Max Act: 2.2661. Min Act: -0.0001

Data Index: 1146237 (C4 (Web Text))

Max Activating Token Index: 227