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

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

Neuron 3354 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0892. Min Range: -1.0892

Max Act: 1.0892. Min Act: -0.0000

Data Index: 36104 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.9477. Min Act: -0.0000

Data Index: 413030 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1284567 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1098151 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.6899. Min Act: -0.0000

Data Index: 694093 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.6636. Min Act: -0.0000

Data Index: 774639 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.6329. Min Act: -0.0000

Data Index: 412471 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.6225. Min Act: -0.0000

Data Index: 149885 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5791. Min Act: -0.0000

Data Index: 933313 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5910. Min Act: -0.0000

Data Index: 937106 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5945. Min Act: -0.0000

Data Index: 677268 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5904. Min Act: -0.0000

Data Index: 243151 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5730. Min Act: -0.0000

Data Index: 384252 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1161193 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5816. Min Act: -0.0000

Data Index: 133628 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5251. Min Act: 0.0000

Data Index: 1235956 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5231. Min Act: -0.0000

Data Index: 364025 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5351. Min Act: -0.0000

Data Index: 214634 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1285774 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.0892. Min Range: -1.0892

Max Act: 0.5028. Min Act: -0.0000

Data Index: 465453 (C4 (Web Text))

Max Activating Token Index: 389