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

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

Neuron 1040 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5942. Min Range: -6.5942

Max Act: 6.5942. Min Act: -0.0000

Data Index: 120648 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 6.5942. Min Range: -6.5942

Max Act: 5.9823. Min Act: -0.0000

Data Index: 1136891 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 6.5942. Min Range: -6.5942

Max Act: 5.7701. Min Act: -0.0000

Data Index: 584993 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 6.5942. Min Range: -6.5942

Max Act: 5.1434. Min Act: -0.0000

Data Index: 395167 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.7421. Min Act: -0.0000

Data Index: 1171374 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.5241. Min Act: -0.0000

Data Index: 535134 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.4635. Min Act: -0.0000

Data Index: 47693 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.2561. Min Act: -0.0000

Data Index: 1126179 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.4242. Min Act: -0.0000

Data Index: 1081907 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.3416. Min Act: -0.0000

Data Index: 948048 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 6.5942. Min Range: -6.5942

Max Act: 3.9711. Min Act: -0.0000

Data Index: 785590 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.2721. Min Act: -0.0000

Data Index: 1092605 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.2347. Min Act: -0.0000

Data Index: 723979 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.3224. Min Act: -0.0000

Data Index: 1271294 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.2994. Min Act: -0.0000

Data Index: 1242004 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 6.5942. Min Range: -6.5942

Max Act: 3.8871. Min Act: -0.0000

Data Index: 133239 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.3759. Min Act: -0.0000

Data Index: 366047 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 6.5942. Min Range: -6.5942

Max Act: 3.8243. Min Act: -0.0000

Data Index: 24346 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 6.5942. Min Range: -6.5942

Max Act: 4.1072. Min Act: -0.0000

Data Index: 586588 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 6.5942. Min Range: -6.5942

Max Act: 3.8858. Min Act: -0.0000

Data Index: 264417 (C4 (Web Text))

Max Activating Token Index: 326