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

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

Neuron 3551 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4861. Min Act: -0.0000

Data Index: 253859 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1356241 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4098. Min Act: -0.0000

Data Index: 591538 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3407. Min Act: -0.0000

Data Index: 636014 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3174. Min Act: -0.0000

Data Index: 568640 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2573. Min Act: -0.0000

Data Index: 249527 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2519. Min Act: -0.0000

Data Index: 232744 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2182. Min Act: -0.0000

Data Index: 197793 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2399. Min Act: -0.0000

Data Index: 390950 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2379. Min Act: -0.0000

Data Index: 665986 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2329. Min Act: -0.0000

Data Index: 553651 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2529. Min Act: -0.0000

Data Index: 328869 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2434. Min Act: -0.0000

Data Index: 553995 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2407. Min Act: -0.0000

Data Index: 8391 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2478. Min Act: -0.0000

Data Index: 783114 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1185060 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1234214 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2249. Min Act: -0.0000

Data Index: 627254 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2309. Min Act: -0.0000

Data Index: 565134 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.2298. Min Act: -0.0000

Data Index: 273533 (C4 (Web Text))

Max Activating Token Index: 813