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

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

Neuron 4397 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.6689. Min Act: -0.0000

Data Index: 1144958 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1304165 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5858. Min Act: -0.0000

Data Index: 618334 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5627. Min Act: -0.0000

Data Index: 608951 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4513. Min Act: -0.0000

Data Index: 51323 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5386. Min Act: -0.0000

Data Index: 192097 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1003550 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5234. Min Act: -0.0000

Data Index: 258583 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5114. Min Act: -0.0000

Data Index: 319738 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1392091 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4727. Min Act: -0.0000

Data Index: 105836 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4733. Min Act: -0.0000

Data Index: 1573625 (Python Code)

Max Activating Token Index: 654

Text #12

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1320402 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4503. Min Act: -0.0000

Data Index: 789591 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4149. Min Act: -0.0000

Data Index: 238892 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1073767 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.3890. Min Act: -0.0000

Data Index: 356252 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.3859. Min Act: -0.0000

Data Index: 381742 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1079325 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.6689. Min Range: -1.6689

Max Act: 1.4565. Min Act: -0.0000

Data Index: 234211 (C4 (Web Text))

Max Activating Token Index: 15