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

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

Neuron 388 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.9494. Min Act: -0.0001

Data Index: 163103 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.8680. Min Act: -0.0001

Data Index: 568724 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.9318. Min Act: -0.0001

Data Index: 1231658 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.7692. Min Act: -0.0001

Data Index: 601151 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.6896. Min Act: -0.0001

Data Index: 641110 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.7367. Min Act: -0.0001

Data Index: 1543574 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.7865. Min Act: -0.0001

Data Index: 1096113 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.7767. Min Act: -0.0001

Data Index: 678110 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.7434. Min Act: -0.0001

Data Index: 101112 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.5763. Min Act: -0.0001

Data Index: 544718 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.4463. Min Act: -0.0001

Data Index: 119336 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.3069. Min Act: -0.0001

Data Index: 1345079 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.5897. Min Act: -0.0001

Data Index: 875838 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.5043. Min Act: -0.0001

Data Index: 933487 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.4497. Min Act: -0.0001

Data Index: 1069165 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.5153. Min Act: -0.0001

Data Index: 124338 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.4679. Min Act: -0.0001

Data Index: 453222 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.5053. Min Act: -0.0001

Data Index: 182784 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.4261. Min Act: -0.0001

Data Index: 470022 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 1.9494. Min Range: -1.9494

Max Act: 1.4707. Min Act: -0.0001

Data Index: 326649 (C4 (Web Text))

Max Activating Token Index: 423