Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1802 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.7324. Min Act: -0.0001

Data Index: 449555 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.7196. Min Act: -0.0001

Data Index: 411455 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.8312. Min Act: -0.0001

Data Index: 798636 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.7887. Min Act: -0.0001

Data Index: 251554 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.7798. Min Act: -0.0001

Data Index: 1168771 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5952. Min Act: -0.0001

Data Index: 773724 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.7154. Min Act: -0.0001

Data Index: 759851 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5823. Min Act: -0.0001

Data Index: 1251467 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.7091. Min Act: -0.0001

Data Index: 1225814 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.6955. Min Act: -0.0001

Data Index: 898366 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5542. Min Act: -0.0001

Data Index: 149057 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.7162. Min Act: -0.0001

Data Index: 982336 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.8540. Min Act: -0.0001

Data Index: 790720 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.8382. Min Act: -0.0001

Data Index: 699915 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5056. Min Act: -0.0001

Data Index: 541174 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.6432. Min Act: -0.0001

Data Index: 310886 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.6391. Min Act: -0.0001

Data Index: 379943 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5988. Min Act: -0.0001

Data Index: 471620 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5446. Min Act: -0.0001

Data Index: 252143 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5436. Min Act: -0.0001

Data Index: 11383 (C4 (Web Text))

Max Activating Token Index: 85