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

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

Neuron 1703 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.4106. Min Act: -0.0000

Data Index: 805558 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.8354. Min Act: -0.0000

Data Index: 1108943 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.8492. Min Act: -0.0000

Data Index: 1114005 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.8409. Min Act: -0.0000

Data Index: 90373 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.7057. Min Act: -0.0000

Data Index: 335302 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.6973. Min Act: -0.0000

Data Index: 1183583 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.8363. Min Act: -0.0000

Data Index: 565094 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.8301. Min Act: -0.0000

Data Index: 1225034 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.7313. Min Act: -0.0000

Data Index: 725843 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.8245. Min Act: -0.0000

Data Index: 841407 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.6915. Min Act: -0.0000

Data Index: 932192 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.9363. Min Act: -0.0000

Data Index: 860727 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.6176. Min Act: -0.0000

Data Index: 102282 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.8723. Min Act: -0.0000

Data Index: 495968 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.7465. Min Act: -0.0000

Data Index: 37502 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.4677. Min Act: -0.0000

Data Index: 326497 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.5892. Min Act: -0.0000

Data Index: 213996 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.6565. Min Act: -0.0000

Data Index: 1161268 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.4440. Min Act: -0.0000

Data Index: 359844 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 3.4106. Min Range: -3.4106

Max Act: 2.4878. Min Act: -0.0000

Data Index: 1086565 (C4 (Web Text))

Max Activating Token Index: 812