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

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

Neuron 346 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1431096 (Python Code)

Max Activating Token Index: 767

Text #1

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1364147 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2927. Min Act: -0.0000

Data Index: 776122 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1447025 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1522785 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1477195 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1370714 (Python Code)

Max Activating Token Index: 671

Text #7

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1221091 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2425. Min Act: -0.0000

Data Index: 958872 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2517. Min Act: -0.0000

Data Index: 438170 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2404. Min Act: -0.0000

Data Index: 58141 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1574756 (Python Code)

Max Activating Token Index: 582

Text #12

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1488403 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2528. Min Act: -0.0000

Data Index: 906973 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1033028 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1387389 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1372152 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1580912 (Python Code)

Max Activating Token Index: 726

Text #18

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1098769 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2274. Min Act: -0.0000

Data Index: 697531 (C4 (Web Text))

Max Activating Token Index: 1011