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

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

Neuron 4845 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1078134 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3277. Min Act: -0.0000

Data Index: 660328 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1272828 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1248375 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2780. Min Act: 0.0001

Data Index: 430798 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2730. Min Act: 0.0002

Data Index: 655546 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2496. Min Act: -0.0000

Data Index: 87131 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2524. Min Act: 0.0000

Data Index: 900611 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2494. Min Act: -0.0000

Data Index: 405299 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1165783 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1253796 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2458. Min Act: 0.0001

Data Index: 391951 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1023645 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1197057 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2206. Min Act: 0.0001

Data Index: 243747 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2182. Min Act: -0.0000

Data Index: 35584 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2209. Min Act: -0.0000

Data Index: 37382 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2214. Min Act: 0.0000

Data Index: 641770 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1073392 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1239900 (C4 (Web Text))

Max Activating Token Index: 438