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

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

Neuron 5253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0872. Min Range: -3.0872

Max Act: 3.0262. Min Act: -0.0000

Data Index: 1084960 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 3.0872. Min Range: -3.0872

Max Act: 3.0169. Min Act: -0.0000

Data Index: 84323 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.8546. Min Act: -0.0000

Data Index: 483208 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.7225. Min Act: -0.0000

Data Index: 1102167 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.7190. Min Act: -0.0000

Data Index: 761043 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.7224. Min Act: -0.0000

Data Index: 725495 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.8522. Min Act: -0.0000

Data Index: 219915 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.6476. Min Act: -0.0000

Data Index: 605485 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 3.0872. Min Range: -3.0872

Max Act: 3.0872. Min Act: -0.0000

Data Index: 779986 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.5228. Min Act: -0.0000

Data Index: 1259058 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.6074. Min Act: -0.0000

Data Index: 585284 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.4366. Min Act: -0.0000

Data Index: 1083375 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.4199. Min Act: -0.0000

Data Index: 159571 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.5181. Min Act: -0.0000

Data Index: 108092 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.4705. Min Act: -0.0000

Data Index: 712579 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.5776. Min Act: -0.0000

Data Index: 925372 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.4711. Min Act: -0.0000

Data Index: 1341987 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.4546. Min Act: -0.0000

Data Index: 493266 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.5311. Min Act: -0.0000

Data Index: 600299 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 3.0872. Min Range: -3.0872

Max Act: 2.3102. Min Act: -0.0000

Data Index: 840997 (C4 (Web Text))

Max Activating Token Index: 290