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

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

Neuron 3104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0002

Data Index: 961348 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0499. Min Act: -0.0002

Data Index: 760004 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1043094 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0498. Min Act: -0.0002

Data Index: 268185 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0489. Min Act: -0.0002

Data Index: 466573 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1195929 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0412. Min Act: -0.0002

Data Index: 754309 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1024836 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0406. Min Act: -0.0002

Data Index: 588008 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0398. Min Act: -0.0002

Data Index: 986947 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1133080 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0398. Min Act: -0.0002

Data Index: 253961 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0388. Min Act: -0.0002

Data Index: 643781 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1655025 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0405. Min Act: -0.0002

Data Index: 530374 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0375. Min Act: -0.0002

Data Index: 931712 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0379. Min Act: -0.0002

Data Index: 110805 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0380. Min Act: -0.0002

Data Index: 777861 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0364. Min Act: -0.0002

Data Index: 713251 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0368. Min Act: -0.0002

Data Index: 889033 (C4 (Web Text))

Max Activating Token Index: 285