Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1935 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.8409. Min Act: -0.0003

Data Index: 580691 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.8110. Min Act: -0.0003

Data Index: 1154178 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.8196. Min Act: -0.0003

Data Index: 1084288 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7537. Min Act: -0.0003

Data Index: 42081 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7652. Min Act: -0.0003

Data Index: 815342 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.8326. Min Act: -0.0003

Data Index: 951513 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7811. Min Act: -0.0003

Data Index: 887043 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7975. Min Act: -0.0003

Data Index: 552538 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7690. Min Act: -0.0003

Data Index: 285493 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7473. Min Act: -0.0003

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7591. Min Act: -0.0003

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7332. Min Act: -0.0003

Data Index: 900141 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7058. Min Act: -0.0003

Data Index: 1351238 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7275. Min Act: -0.0003

Data Index: 730900 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6878. Min Act: -0.0003

Data Index: 940870 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7057. Min Act: -0.0003

Data Index: 24735 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5699. Min Act: -0.0003

Data Index: 576269 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7221. Min Act: -0.0003

Data Index: 1092085 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6777. Min Act: -0.0003

Data Index: 5690 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7461. Min Act: -0.0003

Data Index: 360178 (C4 (Web Text))

Max Activating Token Index: 546