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

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

Neuron 11 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0002

Data Index: 982482 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0633. Min Act: -0.0002

Data Index: 334594 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0616. Min Act: -0.0002

Data Index: 758271 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0602. Min Act: -0.0002

Data Index: 917004 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1054159 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0548. Min Act: -0.0002

Data Index: 185215 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0548. Min Act: -0.0002

Data Index: 741369 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0510. Min Act: -0.0002

Data Index: 950509 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0485. Min Act: -0.0003

Data Index: 157246 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0469. Min Act: -0.0003

Data Index: 72247 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0499. Min Act: -0.0002

Data Index: 767099 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0475. Min Act: -0.0003

Data Index: 561200 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1152788 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1001130 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1137862 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0424. Min Act: -0.0002

Data Index: 395519 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0428. Min Act: -0.0002

Data Index: 391123 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0422. Min Act: -0.0002

Data Index: 448871 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0424. Min Act: -0.0002

Data Index: 923274 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0413. Min Act: -0.0002

Data Index: 951089 (C4 (Web Text))

Max Activating Token Index: 534