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

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

Neuron 5217 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2670. Min Range: -5.2670

Max Act: 5.2670. Min Act: -0.0000

Data Index: 206302 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 5.2670. Min Range: -5.2670

Max Act: 4.7908. Min Act: -0.0000

Data Index: 470539 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 5.2670. Min Range: -5.2670

Max Act: 4.9249. Min Act: -0.0000

Data Index: 530256 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 5.2670. Min Range: -5.2670

Max Act: 4.7347. Min Act: -0.0000

Data Index: 245305 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 5.2670. Min Range: -5.2670

Max Act: 4.1400. Min Act: -0.0000

Data Index: 195932 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.9711. Min Act: -0.0000

Data Index: 1218511 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.9727. Min Act: -0.0000

Data Index: 723918 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 5.2670. Min Range: -5.2670

Max Act: 4.0045. Min Act: -0.0000

Data Index: 794071 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.6703. Min Act: -0.0000

Data Index: 584841 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.9392. Min Act: -0.0000

Data Index: 316292 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.8919. Min Act: -0.0000

Data Index: 304918 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.5219. Min Act: -0.0000

Data Index: 335686 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.9959. Min Act: -0.0000

Data Index: 267254 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.5013. Min Act: -0.0000

Data Index: 952959 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.4630. Min Act: -0.0000

Data Index: 941881 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.6216. Min Act: -0.0000

Data Index: 1093793 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.3935. Min Act: -0.0000

Data Index: 441696 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.5355. Min Act: -0.0000

Data Index: 1193594 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.3273. Min Act: 0.0000

Data Index: 827720 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 5.2670. Min Range: -5.2670

Max Act: 3.4522. Min Act: -0.0000

Data Index: 916070 (C4 (Web Text))

Max Activating Token Index: 601