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

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

Neuron 169 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: 1.4034. Min Range: -1.4034

Max Act: 1.4034. Min Act: -0.0000

Data Index: 645079 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.2964. Min Act: -0.0000

Data Index: 913471 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.1767. Min Act: -0.0000

Data Index: 271447 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.2403. Min Act: -0.0000

Data Index: 640307 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.1390. Min Act: -0.0000

Data Index: 567565 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.1963. Min Act: -0.0000

Data Index: 902495 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0704. Min Act: -0.0000

Data Index: 760019 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.1131. Min Act: -0.0000

Data Index: 449 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0060. Min Act: -0.0000

Data Index: 397701 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8906. Min Act: -0.0000

Data Index: 259087 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1226562 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1023125 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8433. Min Act: -0.0000

Data Index: 602060 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1207806 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9589. Min Act: 0.0000

Data Index: 1023738 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8784. Min Act: 0.0000

Data Index: 92734 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8739. Min Act: -0.0000

Data Index: 886352 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8511. Min Act: -0.0000

Data Index: 409001 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8766. Min Act: -0.0000

Data Index: 758581 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.8912. Min Act: -0.0000

Data Index: 635873 (C4 (Web Text))

Max Activating Token Index: 944