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

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

Neuron 2386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.9597. Min Act: -0.0001

Data Index: 997690 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.5901. Min Act: -0.0001

Data Index: 1164877 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.4488. Min Act: -0.0000

Data Index: 153126 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1026685 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.3561. Min Act: -0.0000

Data Index: 142356 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1235917 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.2152. Min Act: -0.0000

Data Index: 782040 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.2844. Min Act: -0.0000

Data Index: 963870 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.3002. Min Act: -0.0001

Data Index: 935027 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.2552. Min Act: -0.0000

Data Index: 759158 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.2173. Min Act: -0.0000

Data Index: 966275 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.1690. Min Act: -0.0000

Data Index: 55970 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.1355. Min Act: -0.0001

Data Index: 94984 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1042840 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.1301. Min Act: -0.0000

Data Index: 384522 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.0262. Min Act: -0.0001

Data Index: 429754 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.9597. Min Range: -1.9597

Max Act: 0.9760. Min Act: -0.0001

Data Index: 573001 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.9597. Min Range: -1.9597

Max Act: 0.9007. Min Act: -0.0001

Data Index: 1076049 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.9597. Min Range: -1.9597

Max Act: 1.0484. Min Act: -0.0001

Data Index: 1232677 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.9597. Min Range: -1.9597

Max Act: 0.9334. Min Act: -0.0001

Data Index: 1340342 (C4 (Web Text))

Max Activating Token Index: 754