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

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

Neuron 2467 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9104. Min Range: -5.9104

Max Act: 5.9104. Min Act: -0.0001

Data Index: 1274859 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 5.9104. Min Range: -5.9104

Max Act: 5.1906. Min Act: -0.0001

Data Index: 296088 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 5.9104. Min Range: -5.9104

Max Act: 5.7461. Min Act: -0.0001

Data Index: 579199 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 5.9104. Min Range: -5.9104

Max Act: 5.1667. Min Act: -0.0000

Data Index: 865299 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.7595. Min Act: -0.0001

Data Index: 734369 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 5.9104. Min Range: -5.9104

Max Act: 5.5800. Min Act: -0.0001

Data Index: 359314 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.1911. Min Act: -0.0001

Data Index: 1160891 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.3334. Min Act: -0.0001

Data Index: 925437 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 5.9104. Min Range: -5.9104

Max Act: 3.7643. Min Act: -0.0001

Data Index: 786156 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 5.9104. Min Range: -5.9104

Max Act: 3.9161. Min Act: -0.0000

Data Index: 160096 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.2570. Min Act: -0.0001

Data Index: 73880 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.2537. Min Act: -0.0000

Data Index: 215389 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.1522. Min Act: -0.0001

Data Index: 985918 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.3238. Min Act: -0.0001

Data Index: 943922 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.1343. Min Act: -0.0001

Data Index: 516347 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 5.9104. Min Range: -5.9104

Max Act: 3.6895. Min Act: -0.0001

Data Index: 1102410 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 5.9104. Min Range: -5.9104

Max Act: 3.9937. Min Act: -0.0001

Data Index: 1123436 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 5.9104. Min Range: -5.9104

Max Act: 3.9065. Min Act: -0.0001

Data Index: 925423 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 5.9104. Min Range: -5.9104

Max Act: 3.8826. Min Act: -0.0001

Data Index: 955294 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 5.9104. Min Range: -5.9104

Max Act: 4.1921. Min Act: -0.0001

Data Index: 1006250 (C4 (Web Text))

Max Activating Token Index: 463