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

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

Neuron 3071 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: 0.5099. Min Range: -0.5099

Max Act: 0.5099. Min Act: -0.0003

Data Index: 1117050 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4678. Min Act: -0.0003

Data Index: 368833 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4632. Min Act: -0.0003

Data Index: 699538 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4605. Min Act: -0.0003

Data Index: 551156 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4330. Min Act: -0.0003

Data Index: 70982 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4386. Min Act: -0.0003

Data Index: 1355014 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4397. Min Act: -0.0003

Data Index: 45102 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4340. Min Act: -0.0003

Data Index: 76768 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4346. Min Act: -0.0003

Data Index: 1064977 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4446. Min Act: -0.0003

Data Index: 1043561 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4740. Min Act: -0.0003

Data Index: 1223637 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4392. Min Act: -0.0003

Data Index: 1153226 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4384. Min Act: -0.0003

Data Index: 1179286 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4217. Min Act: -0.0003

Data Index: 1183115 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3919. Min Act: -0.0003

Data Index: 98477 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4046. Min Act: -0.0003

Data Index: 347068 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3918. Min Act: -0.0003

Data Index: 579834 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4147. Min Act: -0.0003

Data Index: 1182492 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4260. Min Act: -0.0003

Data Index: 260200 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4359. Min Act: -0.0003

Data Index: 72508 (C4 (Web Text))

Max Activating Token Index: 320