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

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

Neuron 123 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3166. Min Act: -0.0002

Data Index: 1382052 (Python Code)

Max Activating Token Index: 559

Text #1

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3181. Min Act: -0.0002

Data Index: 1499913 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2974. Min Act: -0.0002

Data Index: 1628786 (Python Code)

Max Activating Token Index: 857

Text #3

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2970. Min Act: -0.0002

Data Index: 1569763 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2869. Min Act: -0.0002

Data Index: 1627653 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2970. Min Act: -0.0002

Data Index: 1528788 (Python Code)

Max Activating Token Index: 715

Text #6

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2799. Min Act: -0.0002

Data Index: 1652035 (Python Code)

Max Activating Token Index: 383

Text #7

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2956. Min Act: -0.0002

Data Index: 1482245 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2648. Min Act: -0.0002

Data Index: 962994 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2591. Min Act: -0.0002

Data Index: 454196 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2577. Min Act: -0.0002

Data Index: 1430045 (Python Code)

Max Activating Token Index: 841

Text #11

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2659. Min Act: -0.0002

Data Index: 748232 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2624. Min Act: -0.0002

Data Index: 1586597 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2647. Min Act: -0.0002

Data Index: 1407465 (Python Code)

Max Activating Token Index: 561

Text #14

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2524. Min Act: -0.0002

Data Index: 1436657 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2477. Min Act: -0.0002

Data Index: 1409122 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2389. Min Act: -0.0002

Data Index: 1631388 (Python Code)

Max Activating Token Index: 420

Text #17

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2472. Min Act: -0.0002

Data Index: 1301449 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2450. Min Act: -0.0002

Data Index: 1630634 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2461. Min Act: -0.0002

Data Index: 203117 (C4 (Web Text))

Max Activating Token Index: 820