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

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

Neuron 2920 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1242214 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.3029. Min Act: -0.0000

Data Index: 921754 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.3265. Min Act: -0.0000

Data Index: 392346 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1319421 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2944. Min Act: -0.0000

Data Index: 439145 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.3045. Min Act: -0.0000

Data Index: 380874 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2722. Min Act: -0.0000

Data Index: 892551 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2720. Min Act: -0.0000

Data Index: 671248 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1141019 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1468354 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1410391 (Python Code)

Max Activating Token Index: 503

Text #11

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1014408 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2649. Min Act: -0.0000

Data Index: 973282 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2539. Min Act: -0.0000

Data Index: 595184 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1370211 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1577024 (Python Code)

Max Activating Token Index: 943

Text #16

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1475181 (Python Code)

Max Activating Token Index: 374

Text #17

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1061954 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1207055 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2224. Min Act: -0.0000

Data Index: 111857 (C4 (Web Text))

Max Activating Token Index: 200