Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2381 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.9080. Min Act: -0.0001

Data Index: 431483 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 4.2238. Min Range: -4.2238

Max Act: 4.2238. Min Act: -0.0001

Data Index: 964939 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.8207. Min Act: -0.0001

Data Index: 334794 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.6838. Min Act: -0.0001

Data Index: 599776 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.6714. Min Act: -0.0001

Data Index: 261005 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.8017. Min Act: -0.0001

Data Index: 998177 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.5974. Min Act: -0.0001

Data Index: 785439 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.6164. Min Act: -0.0001

Data Index: 744270 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.7266. Min Act: -0.0001

Data Index: 621680 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.6854. Min Act: -0.0001

Data Index: 1352544 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.2330. Min Act: -0.0001

Data Index: 1252419 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.6096. Min Act: -0.0001

Data Index: 1353799 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.1012. Min Act: -0.0001

Data Index: 1257457 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.1467. Min Act: -0.0001

Data Index: 1008548 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.0417. Min Act: -0.0001

Data Index: 1357308 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.0790. Min Act: -0.0001

Data Index: 543412 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.0693. Min Act: -0.0001

Data Index: 724073 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 4.2238. Min Range: -4.2238

Max Act: 2.9105. Min Act: -0.0001

Data Index: 1343199 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 4.2238. Min Range: -4.2238

Max Act: 3.0283. Min Act: -0.0001

Data Index: 230140 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 4.2238. Min Range: -4.2238

Max Act: 2.8825. Min Act: -0.0001

Data Index: 272227 (C4 (Web Text))

Max Activating Token Index: 429