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

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

Neuron 3485 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3731. Min Range: -1.3731

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1227642 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.3731. Min Range: -1.3731

Max Act: 1.2416. Min Act: -0.0000

Data Index: 387216 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.3731. Min Range: -1.3731

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1094670 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1159263 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.9673. Min Act: -0.0000

Data Index: 670327 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1323757 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8503. Min Act: -0.0000

Data Index: 550044 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1097617 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8852. Min Act: -0.0000

Data Index: 667987 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1160264 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1134063 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.9035. Min Act: 0.0000

Data Index: 1322238 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8441. Min Act: -0.0000

Data Index: 434910 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1118261 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8352. Min Act: -0.0000

Data Index: 343079 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8068. Min Act: -0.0000

Data Index: 293877 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.7491. Min Act: 0.0000

Data Index: 841171 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8480. Min Act: -0.0000

Data Index: 841748 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.8251. Min Act: -0.0000

Data Index: 148382 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.3731. Min Range: -1.3731

Max Act: 0.7731. Min Act: 0.0000

Data Index: 953215 (C4 (Web Text))

Max Activating Token Index: 37