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

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

Neuron 483 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1560645 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3312. Min Act: -0.0001

Data Index: 1573133 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1522362 (Python Code)

Max Activating Token Index: 808

Text #3

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3252. Min Act: -0.0001

Data Index: 1475240 (Python Code)

Max Activating Token Index: 695

Text #4

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1557851 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1654112 (Python Code)

Max Activating Token Index: 630

Text #6

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1534187 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1429232 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2881. Min Act: -0.0001

Data Index: 1527232 (Python Code)

Max Activating Token Index: 919

Text #9

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1411636 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2770. Min Act: -0.0001

Data Index: 1383712 (Python Code)

Max Activating Token Index: 497

Text #11

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1454736 (Python Code)

Max Activating Token Index: 190

Text #12

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1588599 (Python Code)

Max Activating Token Index: 290

Text #13

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1480639 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2633. Min Act: -0.0001

Data Index: 1637731 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1571174 (Python Code)

Max Activating Token Index: 453

Text #16

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1606931 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1564464 (Python Code)

Max Activating Token Index: 618

Text #18

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1452206 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 0.3718. Min Range: -0.3718

Max Act: 0.2565. Min Act: -0.0001

Data Index: 1448453 (Python Code)

Max Activating Token Index: 411