Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2335 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: -0.0000

Data Index: 955211 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1104303 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1142077 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1267436 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1046. Min Act: -0.0001

Data Index: 636818 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1028668 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1073. Min Act: -0.0001

Data Index: 566924 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1013. Min Act: -0.0001

Data Index: 524614 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1000. Min Act: -0.0001

Data Index: 807780 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1343100 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0953. Min Act: -0.0001

Data Index: 156813 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1276247 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1340318 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0886. Min Act: -0.0001

Data Index: 121034 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0921. Min Act: -0.0001

Data Index: 408150 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0951. Min Act: -0.0001

Data Index: 252007 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1052419 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1307561 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1215870 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0832. Min Act: -0.0001

Data Index: 326506 (C4 (Web Text))

Max Activating Token Index: 400