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

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

Neuron 5475 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: 0.6764. Min Range: -0.6764

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1067709 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5822. Min Act: -0.0000

Data Index: 23238 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5494. Min Act: -0.0000

Data Index: 331227 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5521. Min Act: -0.0000

Data Index: 122688 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4666. Min Act: -0.0000

Data Index: 964357 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5835. Min Act: -0.0000

Data Index: 422495 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4408. Min Act: -0.0000

Data Index: 483448 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1169407 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5155. Min Act: -0.0000

Data Index: 331418 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4431. Min Act: -0.0000

Data Index: 526093 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4392. Min Act: -0.0000

Data Index: 497368 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1121657 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4772. Min Act: -0.0000

Data Index: 254690 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1266341 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1287444 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4134. Min Act: -0.0000

Data Index: 396173 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4238. Min Act: -0.0000

Data Index: 58724 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4261. Min Act: -0.0000

Data Index: 418008 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4250. Min Act: -0.0000

Data Index: 30039 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4219. Min Act: -0.0000

Data Index: 692365 (C4 (Web Text))

Max Activating Token Index: 964