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

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

Neuron 918 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3612. Min Act: -0.0000

Data Index: 40054 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3488. Min Act: -0.0000

Data Index: 435351 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1113443 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3304. Min Act: -0.0000

Data Index: 640259 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3372. Min Act: 0.0000

Data Index: 81919 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3091. Min Act: 0.0000

Data Index: 31658 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3172. Min Act: -0.0000

Data Index: 342281 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3069. Min Act: -0.0000

Data Index: 701051 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3270. Min Act: -0.0000

Data Index: 886702 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2931. Min Act: -0.0000

Data Index: 197882 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2935. Min Act: -0.0000

Data Index: 648963 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2671. Min Act: -0.0000

Data Index: 229291 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3012. Min Act: 0.0000

Data Index: 1383551 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2871. Min Act: -0.0000

Data Index: 747638 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1042007 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2815. Min Act: 0.0000

Data Index: 1454481 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1350297 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1394957 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2700. Min Act: -0.0000

Data Index: 318915 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2682. Min Act: -0.0000

Data Index: 936702 (C4 (Web Text))

Max Activating Token Index: 596