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

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

Neuron 3943 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2529. Min Range: -3.2529

Max Act: 3.2529. Min Act: -0.0001

Data Index: 318111 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.7115. Min Act: -0.0000

Data Index: 1247413 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.7578. Min Act: -0.0001

Data Index: 600259 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.6548. Min Act: -0.0000

Data Index: 1257049 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.3278. Min Act: -0.0001

Data Index: 1020940 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.4027. Min Act: -0.0000

Data Index: 599567 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.3949. Min Act: -0.0001

Data Index: 648095 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.2477. Min Act: -0.0000

Data Index: 460802 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.2148. Min Act: -0.0000

Data Index: 592906 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.4536. Min Act: -0.0001

Data Index: 1171618 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.4532. Min Act: -0.0000

Data Index: 671191 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.4262. Min Act: -0.0001

Data Index: 1054624 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.5369. Min Act: -0.0001

Data Index: 501978 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.2800. Min Act: -0.0000

Data Index: 482990 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.1466. Min Act: -0.0001

Data Index: 690089 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.0305. Min Act: -0.0001

Data Index: 187923 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.1248. Min Act: -0.0001

Data Index: 254242 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.2095. Min Act: -0.0001

Data Index: 1117292 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.1864. Min Act: -0.0001

Data Index: 314519 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.2529. Min Range: -3.2529

Max Act: 2.0674. Min Act: -0.0001

Data Index: 610678 (C4 (Web Text))

Max Activating Token Index: 152