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

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

Neuron 2320 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.3364. Min Act: -0.0001

Data Index: 970454 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2823. Min Act: -0.0001

Data Index: 455287 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2673. Min Act: -0.0001

Data Index: 501747 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2624. Min Act: -0.0001

Data Index: 1134862 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2230. Min Act: -0.0001

Data Index: 1638802 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2402. Min Act: -0.0001

Data Index: 1138345 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.3492. Min Act: -0.0001

Data Index: 13106 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2334. Min Act: -0.0001

Data Index: 32314 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2356. Min Act: -0.0001

Data Index: 720710 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1921. Min Act: -0.0001

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1896. Min Act: -0.0001

Data Index: 1278328 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1556. Min Act: -0.0001

Data Index: 530516 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1803. Min Act: -0.0001

Data Index: 1047584 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1851. Min Act: -0.0001

Data Index: 939200 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1357. Min Act: -0.0001

Data Index: 962994 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2505. Min Act: -0.0001

Data Index: 1652669 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1258. Min Act: -0.0001

Data Index: 873764 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1145. Min Act: -0.0001

Data Index: 1388202 (Python Code)

Max Activating Token Index: 383

Text #18

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1883. Min Act: -0.0001

Data Index: 497736 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2450. Min Act: -0.0001

Data Index: 1295577 (C4 (Web Text))

Max Activating Token Index: 255