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

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

Neuron 3307 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: 4.2578. Min Range: -4.2578

Max Act: 4.2578. Min Act: -0.0000

Data Index: 665295 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.8689. Min Act: -0.0000

Data Index: 561819 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.7472. Min Act: -0.0000

Data Index: 103360 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 4.2578. Min Range: -4.2578

Max Act: 4.0799. Min Act: -0.0000

Data Index: 1221994 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.8510. Min Act: -0.0000

Data Index: 1423334 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.8512. Min Act: -0.0000

Data Index: 1228509 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.5190. Min Act: -0.0000

Data Index: 834158 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.7701. Min Act: -0.0000

Data Index: 1555524 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.9208. Min Act: -0.0000

Data Index: 1254136 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.7376. Min Act: -0.0000

Data Index: 837633 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.8472. Min Act: -0.0000

Data Index: 1603606 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.6890. Min Act: -0.0000

Data Index: 1564970 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.4837. Min Act: -0.0000

Data Index: 1513818 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.5923. Min Act: -0.0000

Data Index: 794311 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.5722. Min Act: -0.0000

Data Index: 1549022 (Python Code)

Max Activating Token Index: 642

Text #15

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.4033. Min Act: -0.0000

Data Index: 1431923 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.5169. Min Act: -0.0000

Data Index: 1416347 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.5173. Min Act: -0.0000

Data Index: 553979 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.3406. Min Act: -0.0000

Data Index: 550052 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 4.2578. Min Range: -4.2578

Max Act: 3.4799. Min Act: -0.0000

Data Index: 1447388 (Python Code)

Max Activating Token Index: 937