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

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

Neuron 939 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: 0.4614. Min Range: -0.4614

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1095269 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3333. Min Act: -0.0001

Data Index: 753959 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3064. Min Act: -0.0000

Data Index: 62599 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3187. Min Act: -0.0001

Data Index: 856605 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3057. Min Act: -0.0001

Data Index: 100959 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3113. Min Act: -0.0001

Data Index: 1559425 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1532611 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3170. Min Act: -0.0001

Data Index: 934558 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2833. Min Act: -0.0001

Data Index: 849006 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3340. Min Act: -0.0001

Data Index: 327353 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2810. Min Act: -0.0001

Data Index: 1607001 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2824. Min Act: -0.0001

Data Index: 495070 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1580454 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2839. Min Act: -0.0001

Data Index: 83880 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3065. Min Act: -0.0001

Data Index: 886151 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1652875 (Python Code)

Max Activating Token Index: 494

Text #16

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3160. Min Act: -0.0001

Data Index: 501745 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1166973 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2540. Min Act: -0.0001

Data Index: 97058 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1387712 (Python Code)

Max Activating Token Index: 724