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

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

Neuron 316 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: 0.3566. Min Range: -0.3566

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1265952 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1216680 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3542. Min Act: -0.0000

Data Index: 502806 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3522. Min Act: -0.0000

Data Index: 474700 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3531. Min Act: -0.0000

Data Index: 597724 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3197. Min Act: -0.0000

Data Index: 163498 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1096404 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.3042. Min Act: -0.0000

Data Index: 447358 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1297096 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1012383 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2828. Min Act: -0.0000

Data Index: 405379 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1279082 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2812. Min Act: -0.0000

Data Index: 784487 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2638. Min Act: -0.0000

Data Index: 319011 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2690. Min Act: -0.0000

Data Index: 990538 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2658. Min Act: -0.0000

Data Index: 480425 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1340719 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2660. Min Act: -0.0000

Data Index: 438158 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1247166 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.3566. Min Range: -0.3566

Max Act: 0.2592. Min Act: -0.0000

Data Index: 126649 (C4 (Web Text))

Max Activating Token Index: 200