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

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

Neuron 1107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.8261. Min Act: -0.0001

Data Index: 935993 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.7037. Min Act: -0.0001

Data Index: 527962 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.7041. Min Act: -0.0001

Data Index: 1169690 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.6543. Min Act: -0.0001

Data Index: 444563 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.5614. Min Act: -0.0001

Data Index: 982186 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.7049. Min Act: -0.0001

Data Index: 553588 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.5438. Min Act: -0.0001

Data Index: 277543 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.6609. Min Act: -0.0001

Data Index: 458155 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.4027. Min Act: -0.0001

Data Index: 1170615 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.6542. Min Act: -0.0001

Data Index: 501162 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.5493. Min Act: -0.0001

Data Index: 290078 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.5215. Min Act: -0.0001

Data Index: 1215916 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.5190. Min Act: -0.0001

Data Index: 1308669 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.5213. Min Act: -0.0001

Data Index: 1011622 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.5201. Min Act: -0.0001

Data Index: 586111 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.4844. Min Act: -0.0001

Data Index: 609783 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.4859. Min Act: -0.0001

Data Index: 1352462 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.4820. Min Act: -0.0001

Data Index: 521166 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.4965. Min Act: -0.0001

Data Index: 658778 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.8261. Min Range: -1.8261

Max Act: 1.4542. Min Act: -0.0001

Data Index: 590860 (C4 (Web Text))

Max Activating Token Index: 690