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

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

Neuron 4 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: 1.1411. Min Range: -1.1411

Max Act: 1.0142. Min Act: -0.0001

Data Index: 848826 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.1411. Min Range: -1.1411

Max Act: 1.1411. Min Act: -0.0001

Data Index: 90119 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9417. Min Act: -0.0001

Data Index: 825514 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8005. Min Act: -0.0001

Data Index: 646190 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8954. Min Act: -0.0001

Data Index: 249229 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9549. Min Act: -0.0001

Data Index: 1349181 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.7987. Min Act: -0.0001

Data Index: 851613 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9144. Min Act: -0.0001

Data Index: 1051358 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8685. Min Act: -0.0001

Data Index: 202578 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9619. Min Act: -0.0001

Data Index: 273027 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9060. Min Act: -0.0001

Data Index: 711210 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9215. Min Act: -0.0001

Data Index: 584592 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8417. Min Act: -0.0001

Data Index: 573901 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8390. Min Act: -0.0001

Data Index: 47646 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8311. Min Act: -0.0001

Data Index: 318167 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8010. Min Act: -0.0001

Data Index: 789095 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9520. Min Act: -0.0001

Data Index: 1277018 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1190595 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.9823. Min Act: -0.0001

Data Index: 799343 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.1411. Min Range: -1.1411

Max Act: 0.8467. Min Act: -0.0001

Data Index: 392162 (C4 (Web Text))

Max Activating Token Index: 581