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

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

Neuron 3983 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: 0.1942. Min Range: -0.1942

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1396966 (Python Code)

Max Activating Token Index: 471

Text #1

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1802. Min Act: -0.0001

Data Index: 161257 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1136131 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1489951 (Python Code)

Max Activating Token Index: 872

Text #4

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1698. Min Act: -0.0001

Data Index: 53636 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1670. Min Act: -0.0000

Data Index: 44935 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1680. Min Act: -0.0000

Data Index: 370574 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1582. Min Act: -0.0001

Data Index: 150204 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1462071 (Python Code)

Max Activating Token Index: 463

Text #9

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1189302 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1075383 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1450. Min Act: -0.0001

Data Index: 397596 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1057872 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1473. Min Act: -0.0001

Data Index: 435078 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1461. Min Act: -0.0001

Data Index: 434152 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1463. Min Act: -0.0001

Data Index: 224941 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1559. Min Act: -0.0001

Data Index: 75203 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1489. Min Act: -0.0001

Data Index: 735895 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1437. Min Act: -0.0001

Data Index: 933387 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.1942. Min Range: -0.1942

Max Act: 0.1410. Min Act: -0.0000

Data Index: 863580 (C4 (Web Text))

Max Activating Token Index: 363