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

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

Neuron 1784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1867. Min Range: -3.1867

Max Act: 3.1867. Min Act: -0.0000

Data Index: 1154125 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.5218. Min Act: -0.0000

Data Index: 1299105 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.4954. Min Act: -0.0000

Data Index: 158656 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.7253. Min Act: -0.0000

Data Index: 303690 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.5247. Min Act: -0.0000

Data Index: 341720 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.0842. Min Act: -0.0000

Data Index: 49184 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.1813. Min Act: -0.0000

Data Index: 1309984 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.2663. Min Act: -0.0000

Data Index: 748229 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.4768. Min Act: -0.0000

Data Index: 75952 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.0689. Min Act: -0.0000

Data Index: 1477122 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.0585. Min Act: -0.0000

Data Index: 781762 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.1531. Min Act: -0.0000

Data Index: 1230276 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.1248. Min Act: -0.0000

Data Index: 1358277 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.0892. Min Act: -0.0000

Data Index: 1116494 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.2114. Min Act: -0.0000

Data Index: 698618 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.1967. Min Act: -0.0000

Data Index: 1116252 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 3.1867. Min Range: -3.1867

Max Act: 1.9542. Min Act: -0.0000

Data Index: 65880 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.0530. Min Act: -0.0000

Data Index: 469560 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 3.1867. Min Range: -3.1867

Max Act: 2.0106. Min Act: -0.0000

Data Index: 987481 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 3.1867. Min Range: -3.1867

Max Act: 1.8700. Min Act: -0.0000

Data Index: 102311 (C4 (Web Text))

Max Activating Token Index: 331