Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2121 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8463. Min Act: -0.0001

Data Index: 232439 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8713. Min Act: -0.0001

Data Index: 125099 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8558. Min Act: -0.0001

Data Index: 998619 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8191. Min Act: -0.0001

Data Index: 667175 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7112. Min Act: -0.0001

Data Index: 595160 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8230. Min Act: -0.0001

Data Index: 1168432 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8336. Min Act: -0.0001

Data Index: 1147025 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8321. Min Act: -0.0001

Data Index: 1178398 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7264. Min Act: -0.0001

Data Index: 718393 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7147. Min Act: -0.0001

Data Index: 469100 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7529. Min Act: -0.0001

Data Index: 948393 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7396. Min Act: -0.0001

Data Index: 576085 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6839. Min Act: -0.0001

Data Index: 1117820 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6898. Min Act: -0.0001

Data Index: 644056 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7459. Min Act: -0.0001

Data Index: 254564 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7449. Min Act: -0.0001

Data Index: 934481 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7936. Min Act: -0.0001

Data Index: 245355 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6810. Min Act: -0.0001

Data Index: 1273218 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6732. Min Act: -0.0001

Data Index: 85556 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1210389 (C4 (Web Text))

Max Activating Token Index: 790