Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0003

Data Index: 128494 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0617. Min Act: -0.0002

Data Index: 623090 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1653608 (Python Code)

Max Activating Token Index: 823

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0540. Min Act: -0.0003

Data Index: 169322 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0524. Min Act: -0.0003

Data Index: 986085 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0502. Min Act: -0.0002

Data Index: 361495 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1079610 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0506. Min Act: -0.0003

Data Index: 417486 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1256125 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1059732 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0483. Min Act: -0.0002

Data Index: 493072 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0468. Min Act: -0.0003

Data Index: 228809 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0494. Min Act: -0.0002

Data Index: 775504 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0472. Min Act: -0.0003

Data Index: 631900 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0467. Min Act: -0.0003

Data Index: 503067 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1339348 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0461. Min Act: -0.0002

Data Index: 858931 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1187293 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1193935 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0452. Min Act: -0.0002

Data Index: 557927 (C4 (Web Text))

Max Activating Token Index: 665