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

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

Neuron 5119 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.8254. Min Act: -0.0000

Data Index: 886573 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.9236. Min Act: -0.0000

Data Index: 61864 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.5542. Min Act: -0.0000

Data Index: 1347701 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.5273. Min Act: -0.0000

Data Index: 642491 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.5134. Min Act: -0.0000

Data Index: 792951 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.4863. Min Act: -0.0000

Data Index: 920917 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.4356. Min Act: -0.0000

Data Index: 688871 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.3783. Min Act: -0.0000

Data Index: 726992 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.3927. Min Act: -0.0000

Data Index: 301120 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2853. Min Act: -0.0000

Data Index: 1262407 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2864. Min Act: -0.0000

Data Index: 966570 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2656. Min Act: -0.0000

Data Index: 805279 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2360. Min Act: -0.0000

Data Index: 1037272 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2333. Min Act: -0.0000

Data Index: 186368 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2235. Min Act: -0.0000

Data Index: 19201 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2107. Min Act: -0.0000

Data Index: 645145 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1040476 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2012. Min Act: -0.0000

Data Index: 1281204 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.2041. Min Act: -0.0000

Data Index: 863911 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 2.9236. Min Range: -2.9236

Max Act: 2.1752. Min Act: -0.0000

Data Index: 987131 (C4 (Web Text))

Max Activating Token Index: 40