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

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

Neuron 3578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4665. Min Act: -0.0001

Data Index: 779124 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4687. Min Act: -0.0001

Data Index: 734337 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4663. Min Act: -0.0001

Data Index: 230594 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4524. Min Act: -0.0001

Data Index: 454513 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4438. Min Act: -0.0001

Data Index: 183463 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4514. Min Act: -0.0001

Data Index: 344716 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4226. Min Act: -0.0001

Data Index: 477570 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3777. Min Act: -0.0001

Data Index: 86758 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4367. Min Act: -0.0001

Data Index: 82558 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4248. Min Act: -0.0001

Data Index: 485776 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4374. Min Act: -0.0001

Data Index: 280090 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3886. Min Act: -0.0001

Data Index: 152982 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4049. Min Act: -0.0001

Data Index: 434355 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3833. Min Act: -0.0001

Data Index: 671405 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4167. Min Act: -0.0001

Data Index: 1349595 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3972. Min Act: -0.0001

Data Index: 829411 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4264. Min Act: -0.0001

Data Index: 596238 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1339933 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4119. Min Act: -0.0001

Data Index: 762065 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4015. Min Act: -0.0001

Data Index: 1290528 (C4 (Web Text))

Max Activating Token Index: 542