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

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

Neuron 2343 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.9197. Min Act: -0.0000

Data Index: 626642 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.6121. Min Act: -0.0000

Data Index: 1076673 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.6705. Min Act: -0.0000

Data Index: 1270837 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.8016. Min Act: -0.0000

Data Index: 912834 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.5434. Min Act: -0.0000

Data Index: 900388 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.5475. Min Act: -0.0000

Data Index: 902151 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1250807 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.5871. Min Act: -0.0000

Data Index: 250435 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.3656. Min Act: -0.0000

Data Index: 307698 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.4348. Min Act: -0.0000

Data Index: 350107 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.2568. Min Act: -0.0000

Data Index: 391594 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.3620. Min Act: -0.0000

Data Index: 76624 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.4246. Min Act: -0.0000

Data Index: 361679 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1272835 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1098653 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.3037. Min Act: -0.0000

Data Index: 106414 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.3593. Min Act: -0.0000

Data Index: 212906 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.4399. Min Act: -0.0000

Data Index: 318888 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.1780. Min Act: -0.0000

Data Index: 638972 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.9197. Min Range: -1.9197

Max Act: 1.1919. Min Act: -0.0000

Data Index: 777385 (C4 (Web Text))

Max Activating Token Index: 491