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

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

Neuron 3896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.4843. Min Act: -0.0000

Data Index: 1288696 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.4811. Min Act: -0.0000

Data Index: 623980 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.4483. Min Act: -0.0000

Data Index: 643039 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.3885. Min Act: -0.0000

Data Index: 105364 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.3297. Min Act: -0.0000

Data Index: 158504 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.2524. Min Act: -0.0000

Data Index: 86252 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.2497. Min Act: -0.0000

Data Index: 573609 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.3569. Min Act: -0.0000

Data Index: 213593 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.0573. Min Act: -0.0000

Data Index: 1227255 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.3148. Min Act: -0.0000

Data Index: 535681 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.2827. Min Act: -0.0000

Data Index: 1002185 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.1789. Min Act: -0.0000

Data Index: 391479 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.0318. Min Act: -0.0000

Data Index: 361503 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.3597. Min Act: -0.0000

Data Index: 898281 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.1942. Min Act: -0.0000

Data Index: 600900 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 3.4843. Min Range: -3.4843

Max Act: 1.9295. Min Act: -0.0000

Data Index: 628987 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 3.4843. Min Range: -3.4843

Max Act: 1.9107. Min Act: -0.0000

Data Index: 944943 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.1338. Min Act: -0.0000

Data Index: 982732 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 3.4843. Min Range: -3.4843

Max Act: 1.8999. Min Act: -0.0000

Data Index: 644612 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 3.4843. Min Range: -3.4843

Max Act: 2.0876. Min Act: -0.0000

Data Index: 438522 (C4 (Web Text))

Max Activating Token Index: 250