Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4462 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0597. Min Range: -1.0597

Max Act: 1.0597. Min Act: -0.0000

Data Index: 114241 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.9264. Min Act: -0.0001

Data Index: 951346 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.9431. Min Act: -0.0001

Data Index: 321692 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.9378. Min Act: -0.0001

Data Index: 305060 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8708. Min Act: -0.0001

Data Index: 993133 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8854. Min Act: -0.0001

Data Index: 283549 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8985. Min Act: -0.0001

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8968. Min Act: -0.0001

Data Index: 955649 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8412. Min Act: -0.0001

Data Index: 1357390 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8900. Min Act: -0.0001

Data Index: 421474 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8612. Min Act: -0.0001

Data Index: 1244008 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8946. Min Act: -0.0001

Data Index: 166098 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8614. Min Act: -0.0001

Data Index: 611336 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8554. Min Act: -0.0001

Data Index: 299639 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1263217 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.9097. Min Act: -0.0001

Data Index: 559190 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.9058. Min Act: -0.0001

Data Index: 499338 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.7812. Min Act: -0.0001

Data Index: 1061972 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8128. Min Act: -0.0001

Data Index: 742233 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.0597. Min Range: -1.0597

Max Act: 0.8743. Min Act: -0.0001

Data Index: 492613 (C4 (Web Text))

Max Activating Token Index: 266