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

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

Neuron 3018 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: 0.2682. Min Range: -0.2682

Max Act: 0.2682. Min Act: -0.0002

Data Index: 583148 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2626. Min Act: -0.0002

Data Index: 1098127 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2596. Min Act: -0.0003

Data Index: 1323706 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2579. Min Act: -0.0002

Data Index: 1311260 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2541. Min Act: -0.0002

Data Index: 1192490 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2502. Min Act: -0.0002

Data Index: 804574 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2481. Min Act: -0.0002

Data Index: 935217 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2555. Min Act: -0.0002

Data Index: 874091 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2514. Min Act: -0.0002

Data Index: 300223 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2470. Min Act: -0.0002

Data Index: 195061 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2466. Min Act: -0.0002

Data Index: 52643 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2510. Min Act: -0.0002

Data Index: 134723 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2516. Min Act: -0.0002

Data Index: 1263978 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2494. Min Act: -0.0003

Data Index: 1096764 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2469. Min Act: -0.0003

Data Index: 21589 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2427. Min Act: -0.0002

Data Index: 833796 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2493. Min Act: -0.0002

Data Index: 707680 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2439. Min Act: -0.0002

Data Index: 40776 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2480. Min Act: -0.0002

Data Index: 1052301 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2421. Min Act: -0.0002

Data Index: 1298391 (C4 (Web Text))

Max Activating Token Index: 15