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

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

Neuron 4759 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.1808. Min Act: -0.0002

Data Index: 846515 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0647. Min Act: -0.0002

Data Index: 877871 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0391. Min Act: -0.0002

Data Index: 109507 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9907. Min Act: -0.0002

Data Index: 1096808 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9535. Min Act: -0.0002

Data Index: 199850 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9334. Min Act: -0.0002

Data Index: 40374 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9610. Min Act: -0.0002

Data Index: 1090253 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9536. Min Act: -0.0002

Data Index: 792556 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9473. Min Act: -0.0002

Data Index: 1118865 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9470. Min Act: -0.0002

Data Index: 433409 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9366. Min Act: -0.0002

Data Index: 1290336 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9260. Min Act: -0.0002

Data Index: 333254 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9162. Min Act: -0.0002

Data Index: 1144995 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9258. Min Act: -0.0002

Data Index: 517405 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9110. Min Act: -0.0002

Data Index: 1253549 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9095. Min Act: -0.0002

Data Index: 731320 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9208. Min Act: -0.0002

Data Index: 1163972 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9113. Min Act: -0.0002

Data Index: 137605 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8923. Min Act: -0.0002

Data Index: 1283561 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9125. Min Act: -0.0002

Data Index: 122163 (C4 (Web Text))

Max Activating Token Index: 667