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

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

Neuron 4712 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1019974 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.4184. Min Act: -0.0000

Data Index: 601705 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1765. Min Act: -0.0000

Data Index: 400159 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.3111. Min Act: -0.0000

Data Index: 1227757 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0711. Min Act: -0.0000

Data Index: 524421 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1458199 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1039092 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1614151 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0385. Min Act: -0.0000

Data Index: 221928 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0568. Min Act: -0.0000

Data Index: 895683 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0041. Min Act: -0.0000

Data Index: 557515 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1059167 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.9905. Min Act: -0.0000

Data Index: 266253 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.9186. Min Act: -0.0000

Data Index: 679241 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 1.4184. Min Range: -1.4184

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1544291 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1271964 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1492782 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1172589 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1440958 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 1.4184. Min Range: -1.4184

Max Act: 0.8369. Min Act: -0.0000

Data Index: 664393 (C4 (Web Text))

Max Activating Token Index: 903