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

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

Neuron 3680 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2951. Min Act: -0.0001

Data Index: 318818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2924. Min Act: -0.0001

Data Index: 256870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1244954 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2776. Min Act: -0.0001

Data Index: 779852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2740. Min Act: -0.0001

Data Index: 1045430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2710. Min Act: -0.0002

Data Index: 107284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2669. Min Act: -0.0001

Data Index: 24342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2685. Min Act: -0.0001

Data Index: 952872 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2604. Min Act: -0.0001

Data Index: 34055 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2572. Min Act: -0.0001

Data Index: 1187154 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2562. Min Act: -0.0001

Data Index: 936994 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2545. Min Act: -0.0001

Data Index: 919119 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2508. Min Act: -0.0001

Data Index: 774756 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2504. Min Act: -0.0001

Data Index: 649396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2482. Min Act: -0.0001

Data Index: 48639 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2469. Min Act: -0.0001

Data Index: 844430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2463. Min Act: -0.0002

Data Index: 473817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2491. Min Act: -0.0001

Data Index: 469908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2468. Min Act: -0.0001

Data Index: 766091 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1319205 (C4 (Web Text))

Max Activating Token Index: 3