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

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

Neuron 1801 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.8576. Min Act: -0.0000

Data Index: 392322 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.6392. Min Act: -0.0000

Data Index: 20574 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.6497. Min Act: -0.0000

Data Index: 559566 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.6020. Min Act: -0.0000

Data Index: 498004 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5797. Min Act: -0.0000

Data Index: 25269 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5522. Min Act: -0.0000

Data Index: 772868 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5749. Min Act: -0.0000

Data Index: 671800 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5947. Min Act: -0.0000

Data Index: 433727 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5330. Min Act: -0.0000

Data Index: 686352 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5490. Min Act: -0.0000

Data Index: 234997 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1018128 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5244. Min Act: -0.0000

Data Index: 827519 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5446. Min Act: -0.0000

Data Index: 789785 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5369. Min Act: -0.0000

Data Index: 153022 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5168. Min Act: -0.0000

Data Index: 271308 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.4962. Min Act: -0.0000

Data Index: 426486 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.4936. Min Act: -0.0000

Data Index: 805820 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1220274 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5131. Min Act: -0.0000

Data Index: 408432 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.8576. Min Range: -0.8576

Max Act: 0.5210. Min Act: -0.0000

Data Index: 867302 (C4 (Web Text))

Max Activating Token Index: 99