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

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

Neuron 1369 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0028. Min Range: -1.0028

Max Act: 1.0028. Min Act: 0.0001

Data Index: 753406 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9104. Min Act: 0.0000

Data Index: 90082 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8122. Min Act: 0.0000

Data Index: 287506 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7392. Min Act: -0.0000

Data Index: 122472 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7735. Min Act: 0.0000

Data Index: 777045 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7982. Min Act: 0.0001

Data Index: 229086 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7432. Min Act: 0.0001

Data Index: 1151562 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7438. Min Act: 0.0001

Data Index: 983412 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7122. Min Act: 0.0000

Data Index: 746474 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6644. Min Act: 0.0000

Data Index: 130639 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6371. Min Act: 0.0001

Data Index: 13885 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6634. Min Act: 0.0000

Data Index: 769375 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6931. Min Act: -0.0000

Data Index: 801721 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6874. Min Act: 0.0001

Data Index: 769624 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6659. Min Act: -0.0000

Data Index: 165216 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6620. Min Act: 0.0000

Data Index: 997641 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6600. Min Act: 0.0001

Data Index: 958818 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6668. Min Act: 0.0001

Data Index: 774644 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6379. Min Act: 0.0001

Data Index: 783149 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6196. Min Act: 0.0000

Data Index: 332776 (C4 (Web Text))

Max Activating Token Index: 769