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

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

Neuron 4597 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8773. Min Range: -4.8773

Max Act: 4.8773. Min Act: -0.0000

Data Index: 570242 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.4422. Min Act: -0.0000

Data Index: 1251469 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.6766. Min Act: -0.0000

Data Index: 620398 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.5303. Min Act: -0.0000

Data Index: 354959 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.2028. Min Act: -0.0000

Data Index: 1144467 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.1503. Min Act: -0.0000

Data Index: 1193695 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.1655. Min Act: -0.0000

Data Index: 870535 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.6872. Min Act: -0.0000

Data Index: 632792 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.8030. Min Act: -0.0000

Data Index: 48903 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.8819. Min Act: -0.0000

Data Index: 12412 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.0524. Min Act: -0.0000

Data Index: 493311 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.9613. Min Act: -0.0000

Data Index: 870732 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 4.8773. Min Range: -4.8773

Max Act: 3.0482. Min Act: -0.0000

Data Index: 832972 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.6908. Min Act: -0.0000

Data Index: 970053 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.7002. Min Act: -0.0000

Data Index: 176505 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.9280. Min Act: -0.0000

Data Index: 1327918 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.7522. Min Act: -0.0000

Data Index: 800328 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.7307. Min Act: -0.0000

Data Index: 1132912 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.7073. Min Act: -0.0000

Data Index: 105850 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 4.8773. Min Range: -4.8773

Max Act: 2.5195. Min Act: -0.0000

Data Index: 790983 (C4 (Web Text))

Max Activating Token Index: 226