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

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

Neuron 1474 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: 1.3557. Min Range: -1.3557

Max Act: 1.3557. Min Act: -0.0001

Data Index: 970814 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.2819. Min Act: -0.0001

Data Index: 363519 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.2136. Min Act: -0.0001

Data Index: 833129 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.0901. Min Act: -0.0001

Data Index: 1305957 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.1202. Min Act: -0.0001

Data Index: 318035 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 1.3557. Min Range: -1.3557

Max Act: 1.0576. Min Act: -0.0001

Data Index: 420511 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9859. Min Act: -0.0001

Data Index: 356909 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9904. Min Act: -0.0001

Data Index: 925975 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9654. Min Act: -0.0001

Data Index: 1015313 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9801. Min Act: -0.0001

Data Index: 429848 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9948. Min Act: -0.0001

Data Index: 934384 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9463. Min Act: -0.0001

Data Index: 626079 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8862. Min Act: -0.0001

Data Index: 1243305 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9715. Min Act: -0.0001

Data Index: 18228 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8980. Min Act: -0.0001

Data Index: 96916 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8801. Min Act: -0.0001

Data Index: 30477 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9502. Min Act: -0.0001

Data Index: 1193647 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1287201 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.9054. Min Act: -0.0001

Data Index: 865296 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.3557. Min Range: -1.3557

Max Act: 0.8768. Min Act: -0.0001

Data Index: 1163455 (C4 (Web Text))

Max Activating Token Index: 433