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

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

Neuron 995 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.9142. Min Act: -0.0001

Data Index: 470790 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7934. Min Act: -0.0001

Data Index: 215950 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7898. Min Act: -0.0001

Data Index: 1456542 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7296. Min Act: -0.0001

Data Index: 140848 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7088. Min Act: -0.0001

Data Index: 591783 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7480. Min Act: -0.0001

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7373. Min Act: -0.0001

Data Index: 773944 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1382638 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7460. Min Act: -0.0001

Data Index: 591255 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7180. Min Act: -0.0001

Data Index: 719089 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6012. Min Act: -0.0001

Data Index: 151731 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6409. Min Act: -0.0001

Data Index: 924906 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7515. Min Act: -0.0001

Data Index: 1531017 (Python Code)

Max Activating Token Index: 842

Text #13

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7076. Min Act: -0.0001

Data Index: 1109925 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7362. Min Act: -0.0001

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1536970 (Python Code)

Max Activating Token Index: 545

Text #16

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.7094. Min Act: -0.0001

Data Index: 174737 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6854. Min Act: -0.0001

Data Index: 1285940 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6843. Min Act: -0.0001

Data Index: 370311 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.9142. Min Range: -0.9142

Max Act: 0.6723. Min Act: -0.0001

Data Index: 764672 (C4 (Web Text))

Max Activating Token Index: 825