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

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

Neuron 5208 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7298. Min Range: -7.7298

Max Act: 7.7298. Min Act: -0.0000

Data Index: 1126067 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 7.7298. Min Range: -7.7298

Max Act: 7.0077. Min Act: -0.0000

Data Index: 1158519 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 7.7298. Min Range: -7.7298

Max Act: 6.8254. Min Act: -0.0000

Data Index: 1239343 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 7.7298. Min Range: -7.7298

Max Act: 6.5798. Min Act: -0.0000

Data Index: 976202 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 7.7298. Min Range: -7.7298

Max Act: 6.1451. Min Act: -0.0001

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 7.7298. Min Range: -7.7298

Max Act: 6.9553. Min Act: -0.0001

Data Index: 645828 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 7.7298. Min Range: -7.7298

Max Act: 6.0587. Min Act: -0.0000

Data Index: 520270 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 7.7298. Min Range: -7.7298

Max Act: 6.1285. Min Act: -0.0000

Data Index: 163415 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.5963. Min Act: -0.0000

Data Index: 60885 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.5747. Min Act: -0.0000

Data Index: 1296754 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.4050. Min Act: -0.0001

Data Index: 964815 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.3943. Min Act: -0.0001

Data Index: 1165998 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.5263. Min Act: -0.0000

Data Index: 646980 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.6605. Min Act: -0.0000

Data Index: 897524 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.5064. Min Act: -0.0000

Data Index: 536462 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.5965. Min Act: -0.0000

Data Index: 63648 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.5007. Min Act: -0.0000

Data Index: 350153 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.6753. Min Act: -0.0000

Data Index: 821559 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.3035. Min Act: -0.0001

Data Index: 697382 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 7.7298. Min Range: -7.7298

Max Act: 5.5185. Min Act: -0.0000

Data Index: 82025 (C4 (Web Text))

Max Activating Token Index: 326