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

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

Neuron 3395 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.5350. Min Act: -0.0001

Data Index: 1114463 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4862. Min Act: -0.0001

Data Index: 540431 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4328. Min Act: -0.0001

Data Index: 1192831 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4347. Min Act: -0.0001

Data Index: 155936 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3867. Min Act: -0.0001

Data Index: 173748 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4409. Min Act: -0.0001

Data Index: 75023 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4988. Min Act: -0.0001

Data Index: 636232 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4479. Min Act: -0.0001

Data Index: 899905 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4770. Min Act: -0.0001

Data Index: 1007653 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4211. Min Act: -0.0001

Data Index: 102694 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4103. Min Act: -0.0001

Data Index: 789505 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4162. Min Act: -0.0001

Data Index: 790538 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1229749 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4000. Min Act: -0.0001

Data Index: 77997 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4062. Min Act: -0.0001

Data Index: 998368 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3878. Min Act: -0.0001

Data Index: 193130 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3857. Min Act: -0.0001

Data Index: 641807 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3798. Min Act: -0.0001

Data Index: 544049 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3798. Min Act: -0.0001

Data Index: 609875 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4081. Min Act: -0.0001

Data Index: 913399 (C4 (Web Text))

Max Activating Token Index: 422