Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2494 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3072. Min Act: -0.0001

Data Index: 1413972 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2985. Min Act: -0.0001

Data Index: 1620221 (Python Code)

Max Activating Token Index: 968

Text #2

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1470236 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1533227 (Python Code)

Max Activating Token Index: 514

Text #4

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1426345 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2845. Min Act: -0.0001

Data Index: 652643 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3099. Min Act: -0.0001

Data Index: 1473406 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2835. Min Act: -0.0001

Data Index: 2914 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2585. Min Act: -0.0001

Data Index: 1503166 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1558457 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2627. Min Act: -0.0001

Data Index: 1447273 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1634628 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1535762 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1622781 (Python Code)

Max Activating Token Index: 221

Text #14

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1506591 (Python Code)

Max Activating Token Index: 216

Text #15

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2754. Min Act: -0.0001

Data Index: 1483422 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1533682 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2814. Min Act: -0.0001

Data Index: 72592 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1480118 (Python Code)

Max Activating Token Index: 563

Text #19

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1437865 (Python Code)

Max Activating Token Index: 907