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

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

Neuron 1706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.1243. Min Act: -0.0001

Data Index: 924551 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0836. Min Act: -0.0001

Data Index: 990666 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0833. Min Act: -0.0001

Data Index: 1314492 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9946. Min Act: -0.0001

Data Index: 343427 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0129. Min Act: -0.0001

Data Index: 958435 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.1243. Min Range: -1.1243

Max Act: 1.0306. Min Act: -0.0001

Data Index: 1050251 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8956. Min Act: -0.0001

Data Index: 505077 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9116. Min Act: -0.0001

Data Index: 474289 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9102. Min Act: -0.0001

Data Index: 611694 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9132. Min Act: -0.0001

Data Index: 672440 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.9220. Min Act: -0.0001

Data Index: 40607 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8367. Min Act: -0.0001

Data Index: 546190 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8559. Min Act: -0.0001

Data Index: 123771 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8438. Min Act: -0.0001

Data Index: 687932 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.8413. Min Act: -0.0001

Data Index: 114574 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.7752. Min Act: -0.0001

Data Index: 752014 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.7799. Min Act: -0.0001

Data Index: 114236 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.7788. Min Act: -0.0001

Data Index: 291126 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.7937. Min Act: -0.0001

Data Index: 36040 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.1243. Min Range: -1.1243

Max Act: 0.7790. Min Act: -0.0001

Data Index: 165007 (C4 (Web Text))

Max Activating Token Index: 55