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

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

Neuron 1923 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.8203. Min Act: -0.0000

Data Index: 276564 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1110398 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.6228. Min Act: -0.0000

Data Index: 931915 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.4902. Min Act: -0.0000

Data Index: 503997 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1203172 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.4562. Min Act: -0.0000

Data Index: 48240 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.4517. Min Act: -0.0000

Data Index: 1168815 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1359189 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.4192. Min Act: -0.0000

Data Index: 852149 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1112113 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3896. Min Act: -0.0000

Data Index: 535216 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1127621 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3713. Min Act: 0.0000

Data Index: 31011 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.2851. Min Act: -0.0000

Data Index: 623831 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.2884. Min Act: -0.0000

Data Index: 863292 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3573. Min Act: -0.0000

Data Index: 19485 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3584. Min Act: -0.0000

Data Index: 1302021 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3388. Min Act: 0.0001

Data Index: 980666 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3339. Min Act: -0.0000

Data Index: 683728 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 1.8203. Min Range: -1.8203

Max Act: 1.3273. Min Act: -0.0000

Data Index: 648097 (C4 (Web Text))

Max Activating Token Index: 813