Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3617 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.8469. Min Act: -0.0001

Data Index: 756861 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7674. Min Act: -0.0002

Data Index: 122075 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.8104. Min Act: -0.0002

Data Index: 52988 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7862. Min Act: -0.0001

Data Index: 207312 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1079013 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7557. Min Act: -0.0002

Data Index: 144684 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7529. Min Act: -0.0001

Data Index: 993626 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7500. Min Act: -0.0002

Data Index: 687651 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7712. Min Act: -0.0002

Data Index: 685129 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7160. Min Act: -0.0002

Data Index: 1077884 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7103. Min Act: -0.0002

Data Index: 124829 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7058. Min Act: -0.0002

Data Index: 1105429 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7723. Min Act: -0.0001

Data Index: 541123 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7112. Min Act: -0.0002

Data Index: 752751 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7128. Min Act: -0.0002

Data Index: 201930 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7064. Min Act: -0.0002

Data Index: 358401 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7050. Min Act: -0.0002

Data Index: 561342 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.6677. Min Act: -0.0001

Data Index: 572401 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.6796. Min Act: -0.0002

Data Index: 811827 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.6974. Min Act: -0.0001

Data Index: 849401 (C4 (Web Text))

Max Activating Token Index: 966