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

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

Neuron 3761 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2797. Min Range: -2.2797

Max Act: 2.2797. Min Act: -0.0000

Data Index: 1133880 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.6979. Min Act: -0.0000

Data Index: 1263273 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.5950. Min Act: -0.0000

Data Index: 899558 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.6550. Min Act: -0.0000

Data Index: 834908 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.7154. Min Act: -0.0000

Data Index: 86285 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.6162. Min Act: -0.0000

Data Index: 1577064 (Python Code)

Max Activating Token Index: 528

Text #6

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.5759. Min Act: -0.0000

Data Index: 1390417 (Python Code)

Max Activating Token Index: 561

Text #7

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1281602 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.5430. Min Act: -0.0000

Data Index: 987481 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1247486 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.4950. Min Act: -0.0000

Data Index: 748450 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.4836. Min Act: -0.0000

Data Index: 999503 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1018758 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.6668. Min Act: -0.0000

Data Index: 119102 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.4213. Min Act: -0.0000

Data Index: 209561 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.3421. Min Act: -0.0000

Data Index: 980042 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1348895 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.3174. Min Act: -0.0000

Data Index: 906620 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.4726. Min Act: -0.0000

Data Index: 526785 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 2.2797. Min Range: -2.2797

Max Act: 1.4716. Min Act: -0.0000

Data Index: 570772 (C4 (Web Text))

Max Activating Token Index: 182