Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4702 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3126. Min Range: -1.3126

Max Act: 1.3126. Min Act: -0.0000

Data Index: 792473 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.3126. Min Range: -1.3126

Max Act: 1.1161. Min Act: -0.0000

Data Index: 797558 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.3126. Min Range: -1.3126

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1057044 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 1.3126. Min Range: -1.3126

Max Act: 1.0666. Min Act: -0.0000

Data Index: 615100 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1087585 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1350398 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.9655. Min Act: -0.0000

Data Index: 878114 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1237149 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8243. Min Act: -0.0000

Data Index: 450780 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8495. Min Act: -0.0000

Data Index: 934476 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.9276. Min Act: -0.0000

Data Index: 390347 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8896. Min Act: -0.0000

Data Index: 371445 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1015196 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8563. Min Act: -0.0000

Data Index: 886525 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1206602 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8492. Min Act: -0.0000

Data Index: 385632 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.7760. Min Act: -0.0000

Data Index: 54394 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1253136 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.8286. Min Act: -0.0000

Data Index: 329327 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 1.3126. Min Range: -1.3126

Max Act: 0.7264. Min Act: -0.0000

Data Index: 173540 (C4 (Web Text))

Max Activating Token Index: 220