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

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

Neuron 2835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.4593. Min Act: -0.0001

Data Index: 1103044 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3333. Min Act: -0.0001

Data Index: 1340436 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.1676. Min Act: -0.0001

Data Index: 434627 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.4730. Min Act: -0.0001

Data Index: 964995 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.1526. Min Act: -0.0001

Data Index: 619311 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.1658. Min Act: -0.0001

Data Index: 182728 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.0973. Min Act: -0.0001

Data Index: 1168853 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.0613. Min Act: -0.0001

Data Index: 418569 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.1993. Min Act: -0.0001

Data Index: 769362 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.9178. Min Act: -0.0001

Data Index: 483922 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.7430. Min Act: -0.0001

Data Index: 557250 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.6864. Min Act: -0.0001

Data Index: 320409 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.2439. Min Act: -0.0001

Data Index: 68003 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.8789. Min Act: -0.0001

Data Index: 612034 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.5224. Min Act: -0.0001

Data Index: 948218 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.3471. Min Act: -0.0001

Data Index: 313354 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.6185. Min Act: -0.0001

Data Index: 175815 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.3197. Min Act: -0.0001

Data Index: 1220820 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.4043. Min Act: -0.0001

Data Index: 72012 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 3.4730. Min Range: -3.4730

Max Act: 2.3661. Min Act: -0.0001

Data Index: 992107 (C4 (Web Text))

Max Activating Token Index: 216