Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 127 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.9799. Min Act: -0.0000

Data Index: 168683 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.8161. Min Act: -0.0000

Data Index: 1283253 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.6232. Min Act: -0.0000

Data Index: 282116 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.4075. Min Act: -0.0000

Data Index: 1110355 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.3589. Min Act: -0.0000

Data Index: 1104228 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.4656. Min Act: -0.0000

Data Index: 909558 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 2.9799. Min Range: -2.9799

Max Act: 2.0935. Min Act: -0.0000

Data Index: 1171596 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.8298. Min Act: -0.0000

Data Index: 644931 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.9202. Min Act: -0.0000

Data Index: 1212299 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.9210. Min Act: -0.0000

Data Index: 959015 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.9145. Min Act: -0.0000

Data Index: 629341 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.9014. Min Act: -0.0000

Data Index: 1355324 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.7385. Min Act: -0.0000

Data Index: 713152 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.7243. Min Act: -0.0000

Data Index: 751683 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.6883. Min Act: -0.0000

Data Index: 866498 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.6747. Min Act: -0.0000

Data Index: 291044 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.6174. Min Act: -0.0000

Data Index: 1126090 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.6923. Min Act: -0.0000

Data Index: 1209457 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.5041. Min Act: -0.0000

Data Index: 259176 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 2.9799. Min Range: -2.9799

Max Act: 1.6018. Min Act: -0.0000

Data Index: 1125370 (C4 (Web Text))

Max Activating Token Index: 327