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

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

Neuron 1539 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.7924. Min Act: -0.0000

Data Index: 274963 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.4265. Min Act: -0.0000

Data Index: 659317 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.4651. Min Act: -0.0000

Data Index: 38634 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.5672. Min Act: -0.0000

Data Index: 731190 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.2041. Min Act: -0.0000

Data Index: 266223 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.2303. Min Act: -0.0000

Data Index: 1203536 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.3407. Min Act: -0.0000

Data Index: 123315 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.1073. Min Act: -0.0000

Data Index: 1081926 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.2038. Min Act: -0.0000

Data Index: 200565 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.2833. Min Act: -0.0000

Data Index: 1183346 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.1827. Min Act: -0.0000

Data Index: 199219 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.1738. Min Act: -0.0000

Data Index: 47804 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.2362. Min Act: -0.0000

Data Index: 40431 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.3431. Min Act: -0.0000

Data Index: 597675 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.1959. Min Act: -0.0000

Data Index: 682752 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.1724. Min Act: -0.0000

Data Index: 8472 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.0453. Min Act: -0.0000

Data Index: 907138 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.1420. Min Act: -0.0000

Data Index: 1254920 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.0182. Min Act: -0.0000

Data Index: 1095394 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 2.7924. Min Range: -2.7924

Max Act: 2.1101. Min Act: -0.0000

Data Index: 1000510 (C4 (Web Text))

Max Activating Token Index: 572