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

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

Neuron 2605 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: 0.6224. Min Range: -0.6224

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1114432 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5486. Min Act: -0.0000

Data Index: 85242 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1077353 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.5169. Min Act: -0.0000

Data Index: 557777 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1279335 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4768. Min Act: -0.0000

Data Index: 765999 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4438. Min Act: -0.0000

Data Index: 163964 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4394. Min Act: -0.0000

Data Index: 478055 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4310. Min Act: -0.0000

Data Index: 676508 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1305157 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4583. Min Act: -0.0000

Data Index: 92486 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4371. Min Act: -0.0000

Data Index: 18238 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4530. Min Act: -0.0000

Data Index: 307553 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.3885. Min Act: -0.0000

Data Index: 962126 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4125. Min Act: -0.0000

Data Index: 66387 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.3526. Min Act: -0.0000

Data Index: 157615 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4207. Min Act: -0.0000

Data Index: 482652 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.3316. Min Act: -0.0000

Data Index: 645450 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.3619. Min Act: -0.0000

Data Index: 90865 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.6224. Min Range: -0.6224

Max Act: 0.4152. Min Act: -0.0000

Data Index: 928683 (C4 (Web Text))

Max Activating Token Index: 900