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

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

Neuron 1608 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1235404 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1567243 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6442. Min Act: -0.0000

Data Index: 714412 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1553203 (Python Code)

Max Activating Token Index: 863

Text #4

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6933. Min Act: -0.0000

Data Index: 638928 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1456810 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1583723 (Python Code)

Max Activating Token Index: 665

Text #7

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1000674 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1598313 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1412758 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6186. Min Act: -0.0000

Data Index: 735238 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1550900 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1516380 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6239. Min Act: -0.0000

Data Index: 998378 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1607326 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1470964 (Python Code)

Max Activating Token Index: 756

Text #16

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1401246 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1441142 (Python Code)

Max Activating Token Index: 947

Text #18

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.5748. Min Act: -0.0000

Data Index: 108622 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.8464. Min Range: -0.8464

Max Act: 0.5980. Min Act: -0.0000

Data Index: 675177 (C4 (Web Text))

Max Activating Token Index: 437