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

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

Neuron 2082 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: 1.0469. Min Range: -1.0469

Max Act: 1.0469. Min Act: -0.0001

Data Index: 410875 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9625. Min Act: -0.0001

Data Index: 1171590 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8836. Min Act: -0.0001

Data Index: 876599 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8726. Min Act: -0.0001

Data Index: 593590 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7456. Min Act: -0.0001

Data Index: 1023102 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7595. Min Act: -0.0001

Data Index: 513684 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7543. Min Act: -0.0000

Data Index: 396233 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8568. Min Act: -0.0000

Data Index: 114902 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7687. Min Act: -0.0001

Data Index: 943372 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6960. Min Act: -0.0001

Data Index: 1011962 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7057. Min Act: -0.0001

Data Index: 889964 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6164. Min Act: -0.0001

Data Index: 582968 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1184855 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.5795. Min Act: -0.0001

Data Index: 910200 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7031. Min Act: -0.0001

Data Index: 171152 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7314. Min Act: -0.0001

Data Index: 813804 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6838. Min Act: -0.0000

Data Index: 345983 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6675. Min Act: -0.0001

Data Index: 421052 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6633. Min Act: -0.0001

Data Index: 225571 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7245. Min Act: -0.0001

Data Index: 801143 (C4 (Web Text))

Max Activating Token Index: 615