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

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

Neuron 5042 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.7212. Min Act: -0.0000

Data Index: 151570 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6929. Min Act: -0.0000

Data Index: 897508 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6496. Min Act: -0.0000

Data Index: 379347 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6282. Min Act: -0.0000

Data Index: 126381 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6409. Min Act: -0.0000

Data Index: 386885 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6237. Min Act: -0.0000

Data Index: 8477 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6353. Min Act: -0.0000

Data Index: 367161 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1255764 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1027124 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1143669 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.6353. Min Act: -0.0000

Data Index: 85715 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1009262 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5898. Min Act: -0.0000

Data Index: 718120 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1331159 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1222526 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5697. Min Act: -0.0000

Data Index: 715262 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5792. Min Act: -0.0000

Data Index: 211169 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1331095 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5587. Min Act: -0.0000

Data Index: 757745 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.7212. Min Range: -0.7212

Max Act: 0.5690. Min Act: -0.0000

Data Index: 896017 (C4 (Web Text))

Max Activating Token Index: 613