Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 344 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.8255. Min Act: -0.0000

Data Index: 301411 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.8532. Min Act: -0.0000

Data Index: 555937 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1119550 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6739. Min Act: -0.0000

Data Index: 220233 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1293726 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6851. Min Act: -0.0000

Data Index: 759258 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5944. Min Act: -0.0000

Data Index: 484874 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1093384 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.4973. Min Act: -0.0000

Data Index: 603935 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5479. Min Act: -0.0000

Data Index: 427668 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1247708 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5931. Min Act: -0.0000

Data Index: 295430 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5364. Min Act: -0.0000

Data Index: 141701 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5304. Min Act: -0.0000

Data Index: 414378 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.4891. Min Act: -0.0000

Data Index: 455594 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.4796. Min Act: -0.0000

Data Index: 430614 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.4942. Min Act: -0.0000

Data Index: 330764 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.4784. Min Act: -0.0000

Data Index: 26484 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5098. Min Act: -0.0000

Data Index: 672531 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.4239. Min Act: -0.0000

Data Index: 278258 (C4 (Web Text))

Max Activating Token Index: 196