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

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

Neuron 1579 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1418493 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3055. Min Act: -0.0001

Data Index: 948825 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.3165. Min Act: -0.0001

Data Index: 153940 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2872. Min Act: -0.0000

Data Index: 697927 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1458006 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1392323 (Python Code)

Max Activating Token Index: 912

Text #6

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1400876 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1638423 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1022683 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1373318 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1000542 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2573. Min Act: -0.0000

Data Index: 629260 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2704. Min Act: -0.0000

Data Index: 328120 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1382902 (Python Code)

Max Activating Token Index: 188

Text #14

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1208284 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2651. Min Act: -0.0000

Data Index: 486528 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1632129 (Python Code)

Max Activating Token Index: 894

Text #17

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1118880 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1428958 (Python Code)

Max Activating Token Index: 361

Text #19

Max Range: 0.3764. Min Range: -0.3764

Max Act: 0.2504. Min Act: -0.0000

Data Index: 294031 (C4 (Web Text))

Max Activating Token Index: 157