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

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

Neuron 443 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.8054. Min Act: -0.0001

Data Index: 854033 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.8261. Min Act: -0.0001

Data Index: 372270 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7382. Min Act: -0.0000

Data Index: 686494 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6878. Min Act: -0.0000

Data Index: 767553 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6073. Min Act: -0.0001

Data Index: 937976 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7740. Min Act: -0.0000

Data Index: 437618 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6802. Min Act: -0.0001

Data Index: 1280589 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6351. Min Act: -0.0000

Data Index: 466797 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6731. Min Act: -0.0000

Data Index: 571000 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6439. Min Act: -0.0000

Data Index: 998432 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6018. Min Act: -0.0000

Data Index: 92576 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5605. Min Act: -0.0001

Data Index: 538276 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6161. Min Act: -0.0001

Data Index: 15011 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1329477 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1055022 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5654. Min Act: -0.0000

Data Index: 4422 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5931. Min Act: -0.0000

Data Index: 258648 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1040361 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5444. Min Act: -0.0000

Data Index: 675992 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1158383 (C4 (Web Text))

Max Activating Token Index: 326