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

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

Neuron 731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.2190. Min Act: -0.0000

Data Index: 378089 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.2886. Min Act: -0.0000

Data Index: 1097417 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.0022. Min Act: -0.0000

Data Index: 355058 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8149. Min Act: -0.0000

Data Index: 295568 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.9284. Min Act: -0.0000

Data Index: 544605 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.0388. Min Act: -0.0000

Data Index: 1008376 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8844. Min Act: -0.0000

Data Index: 376262 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.2855. Min Act: -0.0000

Data Index: 370473 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 5.2886. Min Range: -5.2886

Max Act: 3.9560. Min Act: -0.0000

Data Index: 124617 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.1607. Min Act: -0.0000

Data Index: 1107125 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.7333. Min Act: -0.0000

Data Index: 542801 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.4979. Min Act: -0.0000

Data Index: 189538 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.2968. Min Act: -0.0000

Data Index: 1196336 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.5521. Min Act: -0.0000

Data Index: 116920 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.0926. Min Act: -0.0000

Data Index: 15085 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.5786. Min Act: -0.0000

Data Index: 1037768 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.6819. Min Act: -0.0000

Data Index: 970844 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.6689. Min Act: -0.0000

Data Index: 104261 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.3634. Min Act: -0.0000

Data Index: 935910 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.4055. Min Act: -0.0000

Data Index: 1354523 (C4 (Web Text))

Max Activating Token Index: 208