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

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

Neuron 1225 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.5272. Min Act: -0.0000

Data Index: 115623 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.5490. Min Act: -0.0000

Data Index: 829899 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4744. Min Act: -0.0000

Data Index: 146626 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1085430 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1162499 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4271. Min Act: -0.0000

Data Index: 302763 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4147. Min Act: -0.0000

Data Index: 311320 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1144287 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4460. Min Act: -0.0000

Data Index: 262234 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1074402 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1142425 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3801. Min Act: -0.0000

Data Index: 664142 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1037416 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3694. Min Act: -0.0000

Data Index: 922412 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1058758 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1324266 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3746. Min Act: -0.0000

Data Index: 133745 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3367. Min Act: -0.0000

Data Index: 926672 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1129758 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3315. Min Act: -0.0000

Data Index: 419242 (C4 (Web Text))

Max Activating Token Index: 491