Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0538. Min Range: -1.0538

Max Act: 1.0538. Min Act: -0.0003

Data Index: 203022 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.9685. Min Act: -0.0003

Data Index: 444806 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.8576. Min Act: -0.0003

Data Index: 89466 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.9034. Min Act: -0.0003

Data Index: 658157 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.8199. Min Act: -0.0003

Data Index: 872351 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.8515. Min Act: -0.0003

Data Index: 587745 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7764. Min Act: -0.0003

Data Index: 582051 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7930. Min Act: -0.0003

Data Index: 135472 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.8093. Min Act: -0.0003

Data Index: 1141807 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7969. Min Act: -0.0003

Data Index: 772041 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7676. Min Act: -0.0003

Data Index: 20973 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7699. Min Act: -0.0003

Data Index: 651684 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7379. Min Act: -0.0003

Data Index: 682771 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7249. Min Act: -0.0003

Data Index: 911878 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7521. Min Act: -0.0003

Data Index: 1103358 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7545. Min Act: -0.0003

Data Index: 1032367 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7474. Min Act: -0.0003

Data Index: 95750 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7210. Min Act: -0.0003

Data Index: 613520 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7238. Min Act: -0.0003

Data Index: 945195 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.0538. Min Range: -1.0538

Max Act: 0.7456. Min Act: -0.0003

Data Index: 101086 (C4 (Web Text))

Max Activating Token Index: 259