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

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

Neuron 1023 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0237. Min Range: -1.0237

Max Act: 1.0237. Min Act: -0.0000

Data Index: 880552 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.0237. Min Range: -1.0237

Max Act: 1.0065. Min Act: -0.0001

Data Index: 1302925 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.9633. Min Act: -0.0001

Data Index: 803758 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8891. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.9680. Min Act: -0.0000

Data Index: 868908 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8571. Min Act: -0.0001

Data Index: 15738 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8190. Min Act: -0.0001

Data Index: 157186 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.9051. Min Act: -0.0000

Data Index: 761259 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8666. Min Act: -0.0001

Data Index: 13944 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8365. Min Act: -0.0001

Data Index: 450220 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.9024. Min Act: -0.0000

Data Index: 561698 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1281572 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1270022 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.7968. Min Act: -0.0000

Data Index: 390274 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8397. Min Act: -0.0000

Data Index: 913037 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8057. Min Act: -0.0001

Data Index: 503439 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.8231. Min Act: -0.0001

Data Index: 548396 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.7693. Min Act: -0.0000

Data Index: 295680 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.7605. Min Act: -0.0001

Data Index: 310137 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.0237. Min Range: -1.0237

Max Act: 0.7404. Min Act: -0.0000

Data Index: 208214 (C4 (Web Text))

Max Activating Token Index: 985