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

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

Neuron 3121 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3209. Min Range: -5.3209

Max Act: 5.3209. Min Act: -0.0001

Data Index: 1470198 (Python Code)

Max Activating Token Index: 66

Text #1

Max Range: 5.3209. Min Range: -5.3209

Max Act: 5.0046. Min Act: -0.0001

Data Index: 1374509 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 5.3209. Min Range: -5.3209

Max Act: 4.5897. Min Act: -0.0000

Data Index: 1541670 (Python Code)

Max Activating Token Index: 688

Text #3

Max Range: 5.3209. Min Range: -5.3209

Max Act: 4.5595. Min Act: -0.0000

Data Index: 1388982 (Python Code)

Max Activating Token Index: 867

Text #4

Max Range: 5.3209. Min Range: -5.3209

Max Act: 4.2282. Min Act: -0.0000

Data Index: 1564877 (Python Code)

Max Activating Token Index: 902

Text #5

Max Range: 5.3209. Min Range: -5.3209

Max Act: 4.2291. Min Act: -0.0001

Data Index: 1498347 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 5.3209. Min Range: -5.3209

Max Act: 4.0565. Min Act: -0.0000

Data Index: 827878 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.8557. Min Act: -0.0000

Data Index: 1546441 (Python Code)

Max Activating Token Index: 299

Text #8

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.8567. Min Act: -0.0000

Data Index: 1588427 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.9653. Min Act: -0.0001

Data Index: 1626589 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.7661. Min Act: -0.0000

Data Index: 1595158 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.7150. Min Act: -0.0000

Data Index: 1471928 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.8383. Min Act: -0.0001

Data Index: 1534114 (Python Code)

Max Activating Token Index: 328

Text #13

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.6925. Min Act: -0.0000

Data Index: 1592735 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.5178. Min Act: -0.0000

Data Index: 1636472 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.3413. Min Act: -0.0000

Data Index: 1539885 (Python Code)

Max Activating Token Index: 599

Text #16

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.4855. Min Act: -0.0000

Data Index: 1076390 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.3318. Min Act: -0.0000

Data Index: 1507521 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.3343. Min Act: -0.0000

Data Index: 1451174 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 5.3209. Min Range: -5.3209

Max Act: 3.3729. Min Act: -0.0000

Data Index: 1641856 (Python Code)

Max Activating Token Index: 544