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

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

Neuron 2972 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: 0.4350. Min Range: -0.4350

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1353818 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3906. Min Act: -0.0000

Data Index: 691269 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3803. Min Act: -0.0001

Data Index: 268760 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.4100. Min Act: -0.0001

Data Index: 967857 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3775. Min Act: -0.0000

Data Index: 599370 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3690. Min Act: -0.0000

Data Index: 714137 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3566. Min Act: -0.0000

Data Index: 301952 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3789. Min Act: -0.0000

Data Index: 55837 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3479. Min Act: -0.0000

Data Index: 168188 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3196. Min Act: -0.0000

Data Index: 172864 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2977. Min Act: -0.0000

Data Index: 748083 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2944. Min Act: -0.0000

Data Index: 182674 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2968. Min Act: -0.0001

Data Index: 182066 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3083. Min Act: -0.0001

Data Index: 697515 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1279061 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2954. Min Act: -0.0001

Data Index: 736205 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2812. Min Act: -0.0001

Data Index: 50830 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1295926 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1332277 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.2578. Min Act: -0.0001

Data Index: 282556 (C4 (Web Text))

Max Activating Token Index: 180