Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2130 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.0997. Min Act: -0.0000

Data Index: 736416 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.0158. Min Act: -0.0000

Data Index: 17748 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.1334. Min Act: -0.0000

Data Index: 818518 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1085028 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1118252 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.0212. Min Act: -0.0000

Data Index: 868264 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.0212. Min Act: -0.0000

Data Index: 138605 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1002666 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.0580. Min Act: -0.0000

Data Index: 208580 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1309717 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.1371. Min Range: -1.1371

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1433164 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9586. Min Act: -0.0000

Data Index: 379745 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9815. Min Act: -0.0000

Data Index: 768468 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1611546 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9684. Min Act: -0.0000

Data Index: 1353591 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1399230 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9494. Min Act: -0.0001

Data Index: 1362941 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9689. Min Act: -0.0000

Data Index: 229154 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9374. Min Act: -0.0001

Data Index: 231421 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.1371. Min Range: -1.1371

Max Act: 0.9854. Min Act: -0.0001

Data Index: 1294033 (C4 (Web Text))

Max Activating Token Index: 945