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

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

Neuron 1405 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1600022 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1099695 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.3027. Min Act: -0.0000

Data Index: 682289 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1573593 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.3072. Min Act: -0.0000

Data Index: 736424 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1653072 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2732. Min Act: -0.0000

Data Index: 468764 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2700. Min Act: -0.0000

Data Index: 399417 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1646927 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2751. Min Act: -0.0000

Data Index: 117711 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1478329 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1473231 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2607. Min Act: -0.0000

Data Index: 319202 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1460578 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2729. Min Act: -0.0000

Data Index: 409706 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2540. Min Act: -0.0000

Data Index: 778365 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1419109 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1360265 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1536924 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 0.4076. Min Range: -0.4076

Max Act: 0.2595. Min Act: -0.0000

Data Index: 33539 (C4 (Web Text))

Max Activating Token Index: 880