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

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

Neuron 659 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3113. Min Range: -5.3113

Max Act: 5.1651. Min Act: -0.0000

Data Index: 633860 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 5.3113. Min Range: -5.3113

Max Act: 5.3113. Min Act: -0.0000

Data Index: 89549 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.9083. Min Act: -0.0000

Data Index: 1427221 (Python Code)

Max Activating Token Index: 175

Text #3

Max Range: 5.3113. Min Range: -5.3113

Max Act: 5.0727. Min Act: -0.0000

Data Index: 1630727 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 5.3113. Min Range: -5.3113

Max Act: 5.1972. Min Act: -0.0000

Data Index: 1088351 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.9980. Min Act: -0.0000

Data Index: 1613312 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.9631. Min Act: -0.0000

Data Index: 884863 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.8713. Min Act: -0.0000

Data Index: 1477073 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.6702. Min Act: -0.0000

Data Index: 1526646 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.8593. Min Act: -0.0000

Data Index: 1654248 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.6366. Min Act: -0.0000

Data Index: 1427573 (Python Code)

Max Activating Token Index: 464

Text #11

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.6316. Min Act: -0.0000

Data Index: 1556816 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.5906. Min Act: -0.0000

Data Index: 426322 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.7797. Min Act: -0.0000

Data Index: 1382371 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.7408. Min Act: -0.0000

Data Index: 1195345 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.5424. Min Act: -0.0000

Data Index: 1637063 (Python Code)

Max Activating Token Index: 469

Text #16

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.7291. Min Act: -0.0000

Data Index: 1547598 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.8750. Min Act: -0.0000

Data Index: 1384805 (Python Code)

Max Activating Token Index: 817

Text #18

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.8332. Min Act: -0.0000

Data Index: 1613655 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 5.3113. Min Range: -5.3113

Max Act: 4.6472. Min Act: -0.0000

Data Index: 1435483 (Python Code)

Max Activating Token Index: 703