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

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

Neuron 4939 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0001

Data Index: 877983 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0501. Min Act: -0.0001

Data Index: 934938 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1412532 (Python Code)

Max Activating Token Index: 232

Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0489. Min Act: -0.0001

Data Index: 51953 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0481. Min Act: -0.0001

Data Index: 121552 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1560013 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1156921 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0463. Min Act: -0.0001

Data Index: 258128 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0432. Min Act: -0.0001

Data Index: 633964 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1452659 (Python Code)

Max Activating Token Index: 786

Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1618933 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0416. Min Act: -0.0001

Data Index: 12848 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0428. Min Act: -0.0001

Data Index: 106427 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0411. Min Act: -0.0001

Data Index: 4894 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0424. Min Act: -0.0001

Data Index: 921511 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1562368 (Python Code)

Max Activating Token Index: 861

Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0432. Min Act: -0.0001

Data Index: 488182 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0386. Min Act: -0.0001

Data Index: 773619 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1416196 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1000573 (C4 (Web Text))

Max Activating Token Index: 309