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

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

Neuron 4117 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: 0.4004. Min Range: -0.4004

Max Act: 0.3872. Min Act: -0.0000

Data Index: 352415 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.4004. Min Act: -0.0000

Data Index: 83613 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1351543 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3709. Min Act: -0.0000

Data Index: 403102 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3133. Min Act: -0.0000

Data Index: 256584 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1067398 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3339. Min Act: -0.0000

Data Index: 322372 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1077290 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3039. Min Act: -0.0000

Data Index: 256320 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3052. Min Act: -0.0000

Data Index: 195462 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1316203 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2775. Min Act: -0.0000

Data Index: 336633 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1056577 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2823. Min Act: -0.0000

Data Index: 395737 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2900. Min Act: -0.0000

Data Index: 18428 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1061738 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1150126 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2797. Min Act: -0.0000

Data Index: 628328 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2644. Min Act: -0.0000

Data Index: 393438 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2616. Min Act: -0.0000

Data Index: 793972 (C4 (Web Text))

Max Activating Token Index: 157