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

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

Neuron 471 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0000

Data Index: 439243 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1309094 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0560. Min Act: -0.0000

Data Index: 965311 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0499. Min Act: -0.0000

Data Index: 647013 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1268403 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0470. Min Act: -0.0000

Data Index: 899303 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0454. Min Act: -0.0000

Data Index: 915834 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0517. Min Act: -0.0000

Data Index: 876501 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0457. Min Act: -0.0000

Data Index: 362898 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0430. Min Act: -0.0000

Data Index: 700413 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0444. Min Act: -0.0000

Data Index: 1143965 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0419. Min Act: -0.0000

Data Index: 739493 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0443. Min Act: -0.0000

Data Index: 59272 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0428. Min Act: -0.0000

Data Index: 314113 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0438. Min Act: -0.0000

Data Index: 311943 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0439. Min Act: -0.0000

Data Index: 375793 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0438. Min Act: -0.0000

Data Index: 955882 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0440. Min Act: -0.0000

Data Index: 683207 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1279400 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0413. Min Act: -0.0000

Data Index: 602456 (C4 (Web Text))

Max Activating Token Index: 488