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

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

Neuron 5249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0020. Min Range: -2.0020

Max Act: 2.0020. Min Act: -0.0000

Data Index: 1417577 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.9165. Min Act: -0.0000

Data Index: 267190 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1568533 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.8762. Min Act: -0.0000

Data Index: 944693 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1534540 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.6213. Min Act: -0.0000

Data Index: 1519168 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1385099 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1645489 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.5003. Min Act: -0.0000

Data Index: 958591 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1465573 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1520950 (Python Code)

Max Activating Token Index: 688

Text #11

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1497488 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1413921 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.3098. Min Act: -0.0000

Data Index: 715838 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1274050 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.2522. Min Act: -0.0000

Data Index: 1061459 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1111653 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.2725. Min Act: -0.0000

Data Index: 892469 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1594214 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 2.0020. Min Range: -2.0020

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1112444 (C4 (Web Text))

Max Activating Token Index: 141