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

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

Neuron 3104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.4201. Min Act: -0.0001

Data Index: 758578 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0752. Min Act: -0.0001

Data Index: 930190 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0795. Min Act: -0.0002

Data Index: 374251 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0422. Min Act: -0.0002

Data Index: 999812 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0858. Min Act: -0.0002

Data Index: 503925 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0411. Min Act: -0.0001

Data Index: 818389 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0066. Min Act: -0.0001

Data Index: 376043 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0166. Min Act: -0.0001

Data Index: 945254 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0418. Min Act: -0.0001

Data Index: 984694 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0395. Min Act: -0.0001

Data Index: 784375 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9689. Min Act: -0.0002

Data Index: 55278 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9649. Min Act: -0.0001

Data Index: 201951 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9479. Min Act: -0.0002

Data Index: 647477 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9083. Min Act: -0.0001

Data Index: 1123974 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8618. Min Act: -0.0002

Data Index: 157782 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9156. Min Act: -0.0001

Data Index: 970858 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8267. Min Act: -0.0001

Data Index: 117169 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8392. Min Act: -0.0001

Data Index: 685251 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8218. Min Act: -0.0002

Data Index: 1221675 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8569. Min Act: -0.0001

Data Index: 418895 (C4 (Web Text))

Max Activating Token Index: 769