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

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

Neuron 869 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8567. Min Range: -7.8567

Max Act: 7.8567. Min Act: -0.0000

Data Index: 498246 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 7.8567. Min Range: -7.8567

Max Act: 7.3967. Min Act: -0.0000

Data Index: 336555 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 7.8567. Min Range: -7.8567

Max Act: 7.4276. Min Act: -0.0000

Data Index: 921081 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 7.8567. Min Range: -7.8567

Max Act: 6.2689. Min Act: -0.0000

Data Index: 312706 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 7.8567. Min Range: -7.8567

Max Act: 6.2128. Min Act: -0.0000

Data Index: 826960 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 7.8567. Min Range: -7.8567

Max Act: 6.0040. Min Act: -0.0000

Data Index: 758340 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.7920. Min Act: -0.0000

Data Index: 862109 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.6353. Min Act: -0.0000

Data Index: 692777 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.3724. Min Act: -0.0000

Data Index: 372200 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.6144. Min Act: -0.0000

Data Index: 106266 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.7548. Min Act: -0.0000

Data Index: 888828 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.4713. Min Act: -0.0000

Data Index: 618233 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.6404. Min Act: -0.0000

Data Index: 1109988 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 7.8567. Min Range: -7.8567

Max Act: 4.9602. Min Act: -0.0000

Data Index: 1111832 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.4386. Min Act: -0.0000

Data Index: 689691 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.0345. Min Act: -0.0000

Data Index: 947443 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 7.8567. Min Range: -7.8567

Max Act: 4.7740. Min Act: -0.0000

Data Index: 383046 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.7999. Min Act: -0.0000

Data Index: 312465 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.5227. Min Act: -0.0000

Data Index: 893450 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 7.8567. Min Range: -7.8567

Max Act: 5.0934. Min Act: -0.0000

Data Index: 416454 (C4 (Web Text))

Max Activating Token Index: 446