Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 517 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.8300. Min Act: -0.0001

Data Index: 468938 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.8307. Min Act: -0.0000

Data Index: 96742 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1082992 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1338984 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1102622 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1303094 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1345818 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5544. Min Act: -0.0000

Data Index: 211133 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5357. Min Act: -0.0000

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5443. Min Act: -0.0000

Data Index: 799141 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4843. Min Act: -0.0000

Data Index: 665278 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4505. Min Act: -0.0000

Data Index: 298264 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4514. Min Act: -0.0000

Data Index: 896337 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4081. Min Act: -0.0000

Data Index: 422581 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1298691 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4317. Min Act: -0.0000

Data Index: 185225 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1030023 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.3970. Min Act: -0.0000

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1204067 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.3634. Min Act: -0.0000

Data Index: 856551 (C4 (Web Text))

Max Activating Token Index: 562