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

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

Neuron 1919 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.4936. Min Act: -0.0002

Data Index: 525237 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.4396. Min Act: -0.0002

Data Index: 1473247 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.4250. Min Act: -0.0002

Data Index: 1415659 (Python Code)

Max Activating Token Index: 852

Text #3

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.4314. Min Act: -0.0002

Data Index: 1188708 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.3525. Min Act: -0.0002

Data Index: 1638160 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.4052. Min Act: -0.0002

Data Index: 428295 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.3314. Min Act: -0.0002

Data Index: 1621036 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.3526. Min Act: -0.0002

Data Index: 204429 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.3522. Min Act: -0.0002

Data Index: 1540714 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.3179. Min Act: -0.0002

Data Index: 1418898 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.3183. Min Act: -0.0002

Data Index: 1572789 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2970. Min Act: -0.0002

Data Index: 1467334 (Python Code)

Max Activating Token Index: 151

Text #12

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2868. Min Act: -0.0002

Data Index: 318600 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2625. Min Act: -0.0002

Data Index: 1242653 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2675. Min Act: -0.0002

Data Index: 1643402 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2849. Min Act: -0.0002

Data Index: 273525 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2533. Min Act: -0.0002

Data Index: 814481 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2610. Min Act: -0.0002

Data Index: 340826 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2558. Min Act: -0.0002

Data Index: 516515 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.4936. Min Range: -1.4936

Max Act: 1.2475. Min Act: -0.0002

Data Index: 300179 (C4 (Web Text))

Max Activating Token Index: 6