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

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

Neuron 1026 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6627. Min Act: -0.0001

Data Index: 741071 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.7116. Min Act: -0.0001

Data Index: 39006 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6464. Min Act: -0.0001

Data Index: 545960 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1098164 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5510. Min Act: -0.0001

Data Index: 131015 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5613. Min Act: -0.0001

Data Index: 846983 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6121. Min Act: -0.0001

Data Index: 189085 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5724. Min Act: -0.0001

Data Index: 979557 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5639. Min Act: -0.0001

Data Index: 247924 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5630. Min Act: -0.0001

Data Index: 1217999 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5405. Min Act: -0.0001

Data Index: 473183 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5522. Min Act: -0.0001

Data Index: 740577 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4921. Min Act: -0.0001

Data Index: 1101079 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5364. Min Act: -0.0001

Data Index: 159174 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5340. Min Act: -0.0001

Data Index: 604000 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5192. Min Act: -0.0001

Data Index: 542861 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5049. Min Act: -0.0001

Data Index: 734811 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5221. Min Act: -0.0001

Data Index: 1030971 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5349. Min Act: -0.0001

Data Index: 520212 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4889. Min Act: -0.0001

Data Index: 345804 (C4 (Web Text))

Max Activating Token Index: 401