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

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

Neuron 753 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7633. Min Act: -0.0000

Data Index: 134876 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6601. Min Act: -0.0000

Data Index: 968943 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1038540 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6309. Min Act: -0.0000

Data Index: 493281 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6725. Min Act: -0.0001

Data Index: 817213 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1379807 (Python Code)

Max Activating Token Index: 943

Text #6

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6319. Min Act: -0.0000

Data Index: 755048 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6117. Min Act: -0.0001

Data Index: 1200061 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1413634 (Python Code)

Max Activating Token Index: 937

Text #9

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6235. Min Act: -0.0001

Data Index: 332862 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5535. Min Act: -0.0000

Data Index: 230782 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5695. Min Act: -0.0000

Data Index: 248487 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6222. Min Act: -0.0001

Data Index: 1079923 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5782. Min Act: -0.0000

Data Index: 396052 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1268812 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1287644 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1523132 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1124775 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1032536 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1405177 (Python Code)

Max Activating Token Index: 288