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

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

Neuron 2799 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1400. Min Act: -0.0000

Data Index: 423916 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1072321 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1114. Min Act: -0.0000

Data Index: 442059 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0996. Min Act: -0.0000

Data Index: 930040 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1014003 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0988. Min Act: -0.0000

Data Index: 917346 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1028. Min Act: -0.0000

Data Index: 124308 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1032722 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0937. Min Act: -0.0000

Data Index: 814762 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0973. Min Act: -0.0000

Data Index: 272908 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0965. Min Act: -0.0000

Data Index: 797292 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0896. Min Act: -0.0001

Data Index: 295931 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0926. Min Act: -0.0000

Data Index: 92135 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0947. Min Act: -0.0000

Data Index: 612320 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1263713 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0918. Min Act: -0.0000

Data Index: 814054 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1261364 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0910. Min Act: -0.0001

Data Index: 562689 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0906. Min Act: -0.0000

Data Index: 499598 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.0902. Min Act: 0.0000

Data Index: 535338 (C4 (Web Text))

Max Activating Token Index: 256