Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3184 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0965. Min Range: -1.0965

Max Act: 1.0965. Min Act: -0.0001

Data Index: 1175512 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.8210. Min Act: -0.0001

Data Index: 295123 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.8929. Min Act: -0.0001

Data Index: 1652980 (Python Code)

Max Activating Token Index: 89

Text #3

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7340. Min Act: -0.0001

Data Index: 1120728 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1543649 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1583797 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7466. Min Act: -0.0001

Data Index: 1465084 (Python Code)

Max Activating Token Index: 300

Text #7

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1544269 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7075. Min Act: -0.0001

Data Index: 1494627 (Python Code)

Max Activating Token Index: 365

Text #9

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7043. Min Act: -0.0001

Data Index: 1544283 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.7027. Min Act: -0.0001

Data Index: 1583705 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1487318 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6322. Min Act: -0.0000

Data Index: 395350 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6595. Min Act: 0.0000

Data Index: 1510978 (Python Code)

Max Activating Token Index: 181

Text #14

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1505597 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6209. Min Act: 0.0001

Data Index: 1531525 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6343. Min Act: -0.0001

Data Index: 1463354 (Python Code)

Max Activating Token Index: 671

Text #17

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6106. Min Act: -0.0001

Data Index: 1549359 (Python Code)

Max Activating Token Index: 220

Text #18

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1504899 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 1.0965. Min Range: -1.0965

Max Act: 0.5861. Min Act: -0.0001

Data Index: 1104251 (C4 (Web Text))

Max Activating Token Index: 180