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

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

Neuron 1616 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2602. Min Range: -2.2602

Max Act: 2.2602. Min Act: -0.0000

Data Index: 243389 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.5826. Min Act: -0.0000

Data Index: 922302 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.5367. Min Act: -0.0000

Data Index: 970574 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.3926. Min Act: -0.0000

Data Index: 439432 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.4441. Min Act: -0.0000

Data Index: 580044 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.4078. Min Act: -0.0000

Data Index: 779046 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.4541. Min Act: -0.0000

Data Index: 738276 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.5097. Min Act: -0.0000

Data Index: 748585 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.3911. Min Act: -0.0000

Data Index: 979047 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.5091. Min Act: -0.0000

Data Index: 1181504 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.4608. Min Act: -0.0000

Data Index: 446778 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1031136 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.2365. Min Act: -0.0000

Data Index: 884099 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.3051. Min Act: -0.0000

Data Index: 41262 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.6124. Min Act: -0.0000

Data Index: 805927 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.1804. Min Act: -0.0000

Data Index: 425118 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.4098. Min Act: -0.0000

Data Index: 432316 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.3662. Min Act: -0.0000

Data Index: 355876 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.3506. Min Act: -0.0000

Data Index: 770890 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 2.2602. Min Range: -2.2602

Max Act: 1.2422. Min Act: -0.0000

Data Index: 518834 (C4 (Web Text))

Max Activating Token Index: 707