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

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

Neuron 1883 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3226. Min Range: -3.3226

Max Act: 3.2557. Min Act: -0.0001

Data Index: 1634603 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 3.3226. Min Range: -3.3226

Max Act: 3.1345. Min Act: -0.0001

Data Index: 113351 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 3.3226. Min Range: -3.3226

Max Act: 3.0455. Min Act: -0.0001

Data Index: 425906 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 3.3226. Min Range: -3.3226

Max Act: 3.3226. Min Act: -0.0001

Data Index: 1417893 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 3.3226. Min Range: -3.3226

Max Act: 3.0767. Min Act: -0.0001

Data Index: 299481 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.3226. Min Range: -3.3226

Max Act: 3.0502. Min Act: -0.0001

Data Index: 1259046 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.8232. Min Act: -0.0001

Data Index: 1546716 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.9297. Min Act: -0.0001

Data Index: 1543534 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 3.3226. Min Range: -3.3226

Max Act: 3.1686. Min Act: -0.0001

Data Index: 965245 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.9780. Min Act: -0.0001

Data Index: 1147658 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.8218. Min Act: -0.0001

Data Index: 935274 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.7948. Min Act: -0.0001

Data Index: 1367699 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.9273. Min Act: -0.0001

Data Index: 873932 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.8117. Min Act: -0.0001

Data Index: 1590075 (Python Code)

Max Activating Token Index: 533

Text #14

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.5458. Min Act: -0.0001

Data Index: 1426475 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.4881. Min Act: -0.0001

Data Index: 1652244 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.4648. Min Act: -0.0001

Data Index: 1438281 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.5859. Min Act: -0.0001

Data Index: 1454766 (Python Code)

Max Activating Token Index: 236

Text #18

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.6955. Min Act: -0.0001

Data Index: 1414636 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 3.3226. Min Range: -3.3226

Max Act: 2.6843. Min Act: -0.0001

Data Index: 1524418 (Python Code)

Max Activating Token Index: 905