Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 145 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2236. Min Act: -0.0001

Data Index: 861951 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1278430 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1240167 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2193. Min Act: -0.0001

Data Index: 766014 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1982. Min Act: -0.0001

Data Index: 308806 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2017. Min Act: -0.0001

Data Index: 634092 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1854. Min Act: -0.0001

Data Index: 279158 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.2038. Min Act: -0.0001

Data Index: 800936 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1957. Min Act: -0.0001

Data Index: 520168 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1959. Min Act: -0.0001

Data Index: 14369 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1274774 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1790. Min Act: -0.0001

Data Index: 171431 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1430. Min Act: -0.0001

Data Index: 988033 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1329384 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1126039 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1367. Min Act: -0.0001

Data Index: 721300 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1354. Min Act: -0.0001

Data Index: 565917 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1240. Min Act: -0.0001

Data Index: 368106 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1254. Min Act: -0.0001

Data Index: 265035 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.2236. Min Range: -0.2236

Max Act: 0.1408. Min Act: -0.0001

Data Index: 426166 (C4 (Web Text))

Max Activating Token Index: 277