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

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

Neuron 2164 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3677. Min Range: -2.3677

Max Act: 2.3677. Min Act: -0.0000

Data Index: 624494 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 2.3677. Min Range: -2.3677

Max Act: 2.3144. Min Act: -0.0000

Data Index: 1234607 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 2.3677. Min Range: -2.3677

Max Act: 2.2474. Min Act: -0.0000

Data Index: 1323268 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.8956. Min Act: -0.0000

Data Index: 909657 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.8494. Min Act: -0.0000

Data Index: 77440 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.8068. Min Act: -0.0000

Data Index: 581994 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.6977. Min Act: -0.0000

Data Index: 397343 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.8658. Min Act: -0.0000

Data Index: 566352 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.7786. Min Act: -0.0000

Data Index: 888116 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.8645. Min Act: -0.0000

Data Index: 595387 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.7397. Min Act: -0.0000

Data Index: 367179 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.8025. Min Act: -0.0000

Data Index: 46030 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.8053. Min Act: -0.0000

Data Index: 785918 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.6654. Min Act: -0.0000

Data Index: 1177523 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.5800. Min Act: -0.0000

Data Index: 603736 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.6343. Min Act: -0.0000

Data Index: 1299744 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.5384. Min Act: -0.0000

Data Index: 380802 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.5440. Min Act: -0.0000

Data Index: 179174 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1119255 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 2.3677. Min Range: -2.3677

Max Act: 1.3308. Min Act: -0.0000

Data Index: 454079 (C4 (Web Text))

Max Activating Token Index: 720