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

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

Neuron 2213 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: 2.1964. Min Range: -2.1964

Max Act: 2.1964. Min Act: -0.0002

Data Index: 675153 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.7733. Min Act: -0.0002

Data Index: 1335180 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.8433. Min Act: -0.0002

Data Index: 314184 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.7416. Min Act: -0.0002

Data Index: 216569 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.7437. Min Act: -0.0002

Data Index: 934307 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.7614. Min Act: -0.0002

Data Index: 562853 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6932. Min Act: -0.0002

Data Index: 150394 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.7063. Min Act: -0.0002

Data Index: 1092628 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.7093. Min Act: -0.0002

Data Index: 157869 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6852. Min Act: -0.0002

Data Index: 848264 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6710. Min Act: -0.0002

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6514. Min Act: -0.0002

Data Index: 1002560 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6427. Min Act: -0.0002

Data Index: 973495 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6587. Min Act: -0.0002

Data Index: 470421 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6233. Min Act: -0.0002

Data Index: 703170 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.5914. Min Act: -0.0002

Data Index: 161781 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6579. Min Act: -0.0002

Data Index: 605107 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6288. Min Act: -0.0002

Data Index: 1288661 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.6163. Min Act: -0.0002

Data Index: 644565 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 2.1964. Min Range: -2.1964

Max Act: 1.5905. Min Act: -0.0002

Data Index: 499165 (C4 (Web Text))

Max Activating Token Index: 18