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

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

Neuron 854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0909. Min Range: -3.0909

Max Act: 3.0909. Min Act: -0.0000

Data Index: 75376 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 3.0909. Min Range: -3.0909

Max Act: 3.0448. Min Act: -0.0000

Data Index: 870307 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.0909. Min Range: -3.0909

Max Act: 2.9834. Min Act: -0.0000

Data Index: 826040 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 3.0909. Min Range: -3.0909

Max Act: 2.6932. Min Act: -0.0000

Data Index: 807857 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.0909. Min Range: -3.0909

Max Act: 2.5618. Min Act: -0.0000

Data Index: 383387 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.0909. Min Range: -3.0909

Max Act: 2.6505. Min Act: -0.0000

Data Index: 156261 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 3.0909. Min Range: -3.0909

Max Act: 2.3933. Min Act: -0.0000

Data Index: 577056 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.0909. Min Range: -3.0909

Max Act: 2.1587. Min Act: -0.0000

Data Index: 108384 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.7088. Min Act: -0.0000

Data Index: 175365 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 3.0909. Min Range: -3.0909

Max Act: 2.0049. Min Act: -0.0000

Data Index: 62773 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.8803. Min Act: -0.0000

Data Index: 1183423 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.7140. Min Act: -0.0000

Data Index: 900589 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.7160. Min Act: -0.0000

Data Index: 618261 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.7044. Min Act: -0.0000

Data Index: 23265 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.7952. Min Act: -0.0000

Data Index: 330528 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.5405. Min Act: -0.0000

Data Index: 1244471 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.8150. Min Act: -0.0000

Data Index: 878331 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.5934. Min Act: -0.0000

Data Index: 892685 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.6391. Min Act: -0.0000

Data Index: 229003 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 3.0909. Min Range: -3.0909

Max Act: 1.5484. Min Act: -0.0000

Data Index: 1267071 (C4 (Web Text))

Max Activating Token Index: 718