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

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

Neuron 2340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2134. Min Range: -2.2134

Max Act: 2.2134. Min Act: -0.0000

Data Index: 211400 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.6773. Min Act: -0.0000

Data Index: 519566 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.4147. Min Act: -0.0000

Data Index: 388274 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.5028. Min Act: -0.0000

Data Index: 196264 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.4391. Min Act: -0.0000

Data Index: 914235 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.4148. Min Act: -0.0000

Data Index: 104119 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.3989. Min Act: -0.0000

Data Index: 726651 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.2301. Min Act: -0.0000

Data Index: 427106 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.4565. Min Act: -0.0000

Data Index: 370430 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.3693. Min Act: -0.0000

Data Index: 402272 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.4508. Min Act: -0.0000

Data Index: 748018 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.3570. Min Act: -0.0000

Data Index: 783628 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1191890 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1361650 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.2103. Min Act: -0.0000

Data Index: 150913 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1111591 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.2341. Min Act: -0.0000

Data Index: 246458 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.2124. Min Act: -0.0000

Data Index: 317986 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.2584. Min Act: -0.0000

Data Index: 983858 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 2.2134. Min Range: -2.2134

Max Act: 1.0961. Min Act: -0.0000

Data Index: 94464 (C4 (Web Text))

Max Activating Token Index: 953