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

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

Neuron 1504 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: 0.6875. Min Range: -0.6875

Max Act: 0.6875. Min Act: -0.0000

Data Index: 838584 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5980. Min Act: -0.0000

Data Index: 102041 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1095890 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5919. Min Act: 0.0000

Data Index: 662777 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6071. Min Act: -0.0000

Data Index: 741136 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5774. Min Act: 0.0000

Data Index: 174046 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5984. Min Act: -0.0000

Data Index: 327604 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5636. Min Act: 0.0000

Data Index: 1165140 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5733. Min Act: -0.0000

Data Index: 911905 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1316471 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5404. Min Act: -0.0000

Data Index: 128654 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5037. Min Act: -0.0000

Data Index: 541877 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5128. Min Act: -0.0000

Data Index: 145148 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5521. Min Act: -0.0000

Data Index: 480063 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4946. Min Act: -0.0000

Data Index: 677657 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1228313 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4956. Min Act: -0.0000

Data Index: 774883 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5293. Min Act: -0.0000

Data Index: 157401 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5219. Min Act: -0.0000

Data Index: 24697 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5079. Min Act: -0.0000

Data Index: 392353 (C4 (Web Text))

Max Activating Token Index: 649