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

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

Neuron 4028 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: 0.5301. Min Range: -0.5301

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1237318 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.5100. Min Act: -0.0000

Data Index: 353633 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.5146. Min Act: -0.0001

Data Index: 762757 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.4013. Min Act: -0.0000

Data Index: 274815 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3590. Min Act: -0.0001

Data Index: 138319 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.4333. Min Act: -0.0000

Data Index: 710910 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.4314. Min Act: -0.0000

Data Index: 463592 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1330119 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.4055. Min Act: -0.0000

Data Index: 676638 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3964. Min Act: -0.0000

Data Index: 857813 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3920. Min Act: -0.0001

Data Index: 1102963 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.4061. Min Act: -0.0001

Data Index: 921789 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1109042 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.4111. Min Act: -0.0000

Data Index: 53278 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3400. Min Act: -0.0001

Data Index: 106350 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1012318 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3969. Min Act: -0.0001

Data Index: 139 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3388. Min Act: -0.0001

Data Index: 1351936 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3631. Min Act: -0.0001

Data Index: 760754 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.5301. Min Range: -0.5301

Max Act: 0.3523. Min Act: -0.0001

Data Index: 1061019 (C4 (Web Text))

Max Activating Token Index: 256