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

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

Neuron 396 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: 1.4404. Min Range: -1.4404

Max Act: 1.4404. Min Act: -0.0001

Data Index: 164750 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.2602. Min Act: -0.0001

Data Index: 1352228 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1605. Min Act: -0.0001

Data Index: 931949 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1204. Min Act: -0.0001

Data Index: 89510 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1111. Min Act: -0.0001

Data Index: 163691 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1228. Min Act: -0.0001

Data Index: 1254362 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1116. Min Act: -0.0001

Data Index: 1129201 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.1765. Min Act: -0.0001

Data Index: 1126929 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.0114. Min Act: -0.0001

Data Index: 496322 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.4404. Min Range: -1.4404

Max Act: 1.0132. Min Act: -0.0001

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.9935. Min Act: -0.0001

Data Index: 1309163 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.9883. Min Act: -0.0001

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.9422. Min Act: -0.0001

Data Index: 1005624 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.9645. Min Act: -0.0001

Data Index: 1092376 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.9401. Min Act: -0.0001

Data Index: 26350 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.8743. Min Act: -0.0001

Data Index: 223516 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1232068 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.8952. Min Act: -0.0001

Data Index: 795836 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.8632. Min Act: -0.0001

Data Index: 215965 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.4404. Min Range: -1.4404

Max Act: 0.9159. Min Act: -0.0001

Data Index: 357253 (C4 (Web Text))

Max Activating Token Index: 47