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

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

Neuron 1822 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.4284. Min Act: -0.0001

Data Index: 1470919 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.3050. Min Act: -0.0001

Data Index: 1618926 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2790. Min Act: -0.0001

Data Index: 1582220 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1733. Min Act: -0.0001

Data Index: 1440287 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1673. Min Act: -0.0001

Data Index: 1539905 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1352. Min Act: -0.0001

Data Index: 1648282 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0854. Min Act: -0.0001

Data Index: 1525616 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0206. Min Act: -0.0001

Data Index: 1468377 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9912. Min Act: -0.0001

Data Index: 1599580 (Python Code)

Max Activating Token Index: 342

Text #9

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0857. Min Act: -0.0001

Data Index: 1630883 (Python Code)

Max Activating Token Index: 813

Text #10

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1455337 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9668. Min Act: -0.0001

Data Index: 1552823 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9970. Min Act: -0.0001

Data Index: 1616403 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.8607. Min Act: -0.0001

Data Index: 1545049 (Python Code)

Max Activating Token Index: 498

Text #14

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9068. Min Act: -0.0001

Data Index: 1610292 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9965. Min Act: -0.0001

Data Index: 1393512 (Python Code)

Max Activating Token Index: 88

Text #16

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0159. Min Act: -0.0001

Data Index: 1460502 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1402051 (Python Code)

Max Activating Token Index: 738

Text #18

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9695. Min Act: -0.0001

Data Index: 1651274 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9560. Min Act: -0.0001

Data Index: 1518180 (Python Code)

Max Activating Token Index: 442