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

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

Neuron 2737 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1076. Min Range: -2.1076

Max Act: 2.1076. Min Act: -0.0000

Data Index: 452438 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.9827. Min Act: -0.0000

Data Index: 129306 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.8233. Min Act: 0.0000

Data Index: 403016 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.5221. Min Act: -0.0000

Data Index: 1101840 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.5987. Min Act: -0.0000

Data Index: 479416 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1237232 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.4325. Min Act: -0.0000

Data Index: 1098366 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1254081 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.3305. Min Act: -0.0000

Data Index: 592828 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.4602. Min Act: 0.0000

Data Index: 806480 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.5058. Min Act: -0.0000

Data Index: 928285 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.3224. Min Act: -0.0000

Data Index: 580783 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1278209 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.3562. Min Act: -0.0000

Data Index: 1047676 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.3323. Min Act: -0.0000

Data Index: 1181364 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1151622 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1074190 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.2537. Min Act: 0.0000

Data Index: 314524 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.2449. Min Act: -0.0000

Data Index: 320686 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 2.1076. Min Range: -2.1076

Max Act: 1.2288. Min Act: 0.0000

Data Index: 385933 (C4 (Web Text))

Max Activating Token Index: 60