Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2111 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.9831. Min Act: -0.0000

Data Index: 36040 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.9046. Min Act: -0.0000

Data Index: 180159 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1358823 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.8221. Min Act: -0.0000

Data Index: 318164 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.8104. Min Act: -0.0000

Data Index: 563655 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.7980. Min Act: -0.0000

Data Index: 649254 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1513034 (Python Code)

Max Activating Token Index: 915

Text #7

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1021974 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.7766. Min Act: -0.0000

Data Index: 796572 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1154925 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1070114 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1615766 (Python Code)

Max Activating Token Index: 746

Text #12

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1174068 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6633. Min Act: -0.0000

Data Index: 477205 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1278216 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.7051. Min Act: -0.0000

Data Index: 671771 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1228826 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6487. Min Act: -0.0000

Data Index: 735439 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.6374. Min Act: -0.0000

Data Index: 181270 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.9831. Min Range: -0.9831

Max Act: 0.5978. Min Act: -0.0000

Data Index: 19917 (C4 (Web Text))

Max Activating Token Index: 275