Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1221. Min Range: -3.1221

Max Act: 3.1142. Min Act: -0.0001

Data Index: 993614 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 3.1221. Min Range: -3.1221

Max Act: 3.0728. Min Act: -0.0001

Data Index: 1153020 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 3.1221. Min Range: -3.1221

Max Act: 3.0637. Min Act: -0.0001

Data Index: 508748 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 3.1221. Min Range: -3.1221

Max Act: 3.0554. Min Act: -0.0001

Data Index: 895274 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 3.1221. Min Range: -3.1221

Max Act: 3.1221. Min Act: -0.0001

Data Index: 231707 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.8147. Min Act: -0.0001

Data Index: 489499 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.9298. Min Act: -0.0001

Data Index: 1124150 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.7915. Min Act: -0.0001

Data Index: 627473 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.8989. Min Act: -0.0001

Data Index: 358062 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.8080. Min Act: -0.0001

Data Index: 822371 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.7098. Min Act: -0.0001

Data Index: 635257 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.6785. Min Act: -0.0001

Data Index: 720763 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.6801. Min Act: -0.0001

Data Index: 957350 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.5339. Min Act: -0.0001

Data Index: 296881 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.7935. Min Act: -0.0001

Data Index: 730186 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.7846. Min Act: -0.0001

Data Index: 958017 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.7874. Min Act: -0.0001

Data Index: 64099 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.6522. Min Act: -0.0001

Data Index: 1102628 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.6242. Min Act: -0.0001

Data Index: 884737 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.4825. Min Act: -0.0001

Data Index: 501476 (C4 (Web Text))

Max Activating Token Index: 956