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

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

Neuron 2048 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: 1.1985. Min Range: -1.1985

Max Act: 1.1985. Min Act: -0.0001

Data Index: 612532 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 1.1985. Min Range: -1.1985

Max Act: 1.1342. Min Act: -0.0001

Data Index: 31543 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 1.1985. Min Range: -1.1985

Max Act: 1.0221. Min Act: -0.0001

Data Index: 128888 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9907. Min Act: -0.0001

Data Index: 942233 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.1985. Min Range: -1.1985

Max Act: 1.0051. Min Act: -0.0001

Data Index: 612253 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.1985. Min Range: -1.1985

Max Act: 1.0287. Min Act: -0.0001

Data Index: 349956 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.1985. Min Range: -1.1985

Max Act: 1.0565. Min Act: -0.0001

Data Index: 567014 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.1985. Min Range: -1.1985

Max Act: 1.0169. Min Act: -0.0001

Data Index: 1027471 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9401. Min Act: -0.0001

Data Index: 848056 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9398. Min Act: -0.0001

Data Index: 1249933 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9527. Min Act: -0.0001

Data Index: 1221956 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9675. Min Act: -0.0001

Data Index: 248922 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9247. Min Act: -0.0001

Data Index: 688851 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9036. Min Act: -0.0001

Data Index: 469854 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9933. Min Act: -0.0001

Data Index: 703880 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9054. Min Act: -0.0001

Data Index: 943848 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9557. Min Act: -0.0001

Data Index: 650994 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9126. Min Act: -0.0001

Data Index: 647660 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.9012. Min Act: -0.0001

Data Index: 1349474 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.1985. Min Range: -1.1985

Max Act: 0.8888. Min Act: -0.0001

Data Index: 227595 (C4 (Web Text))

Max Activating Token Index: 113