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

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

Neuron 5600 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: 5.1242. Min Range: -5.1242

Max Act: 4.8904. Min Act: 0.0000

Data Index: 470974 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 5.1242. Min Range: -5.1242

Max Act: 4.9378. Min Act: -0.0000

Data Index: 1326541 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 5.1242. Min Range: -5.1242

Max Act: 5.1242. Min Act: -0.0000

Data Index: 10371 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.6134. Min Act: -0.0000

Data Index: 983083 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.5729. Min Act: -0.0000

Data Index: 422974 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.6200. Min Act: -0.0000

Data Index: 1323277 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.2404. Min Act: -0.0000

Data Index: 1294180 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.0376. Min Act: -0.0000

Data Index: 1269033 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.3085. Min Act: -0.0000

Data Index: 1010139 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.0808. Min Act: -0.0000

Data Index: 902011 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 5.1242. Min Range: -5.1242

Max Act: 3.5372. Min Act: -0.0000

Data Index: 804514 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.6731. Min Act: -0.0000

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.9196. Min Act: -0.0000

Data Index: 1337095 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.8198. Min Act: -0.0000

Data Index: 277075 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.9382. Min Act: -0.0000

Data Index: 592902 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.8360. Min Act: 0.0000

Data Index: 607784 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.6395. Min Act: -0.0000

Data Index: 751484 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.6183. Min Act: -0.0000

Data Index: 250596 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.6046. Min Act: -0.0000

Data Index: 36355 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 5.1242. Min Range: -5.1242

Max Act: 2.4372. Min Act: -0.0000

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 64