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

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

Neuron 583 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4924. Min Range: -4.4924

Max Act: 4.4924. Min Act: -0.0000

Data Index: 972330 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 4.4924. Min Range: -4.4924

Max Act: 4.1779. Min Act: -0.0000

Data Index: 613762 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 4.4924. Min Range: -4.4924

Max Act: 3.5668. Min Act: -0.0000

Data Index: 722776 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 4.4924. Min Range: -4.4924

Max Act: 3.2998. Min Act: -0.0000

Data Index: 613148 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 4.4924. Min Range: -4.4924

Max Act: 3.3298. Min Act: -0.0000

Data Index: 135518 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 4.4924. Min Range: -4.4924

Max Act: 3.0714. Min Act: -0.0000

Data Index: 688719 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 4.4924. Min Range: -4.4924

Max Act: 3.1788. Min Act: -0.0000

Data Index: 573037 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.9234. Min Act: -0.0000

Data Index: 1243189 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.8956. Min Act: -0.0000

Data Index: 206893 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 4.4924. Min Range: -4.4924

Max Act: 3.0466. Min Act: -0.0000

Data Index: 57041 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.9870. Min Act: -0.0000

Data Index: 133933 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.9557. Min Act: -0.0000

Data Index: 56000 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.7699. Min Act: -0.0000

Data Index: 1295038 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.8719. Min Act: -0.0000

Data Index: 452116 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.7550. Min Act: -0.0000

Data Index: 829463 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.6766. Min Act: -0.0000

Data Index: 113518 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 4.4924. Min Range: -4.4924

Max Act: 3.1455. Min Act: -0.0000

Data Index: 115887 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.7466. Min Act: -0.0000

Data Index: 516557 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.4714. Min Act: -0.0000

Data Index: 634088 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 4.4924. Min Range: -4.4924

Max Act: 2.5234. Min Act: -0.0000

Data Index: 968392 (C4 (Web Text))

Max Activating Token Index: 745