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

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

Neuron 2039 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1254002 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1272423 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1233. Min Act: -0.0001

Data Index: 568501 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1482896 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1243. Min Act: -0.0001

Data Index: 967925 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1210. Min Act: -0.0001

Data Index: 976058 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1080. Min Act: -0.0001

Data Index: 906924 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1229852 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1067. Min Act: -0.0000

Data Index: 916258 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1032. Min Act: -0.0000

Data Index: 900759 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1081. Min Act: -0.0000

Data Index: 984132 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1078. Min Act: -0.0001

Data Index: 246689 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1151496 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1422387 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1185845 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1309430 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.0943. Min Act: -0.0000

Data Index: 609995 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.0974. Min Act: -0.0001

Data Index: 673361 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.0984. Min Act: -0.0000

Data Index: 244528 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.0986. Min Act: -0.0000

Data Index: 702130 (C4 (Web Text))

Max Activating Token Index: 501