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

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

Neuron 462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2406. Min Range: -1.2406

Max Act: 1.2406. Min Act: -0.0000

Data Index: 1232257 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1200879 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.8475. Min Act: -0.0000

Data Index: 611593 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.8178. Min Act: -0.0000

Data Index: 262607 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1429304 (Python Code)

Max Activating Token Index: 662

Text #5

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1003990 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1101888 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.6086. Min Act: -0.0000

Data Index: 383610 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1500331 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.6142. Min Act: -0.0000

Data Index: 334852 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.6026. Min Act: -0.0000

Data Index: 799154 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1455617 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5464. Min Act: -0.0000

Data Index: 93177 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5791. Min Act: -0.0000

Data Index: 533250 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1545533 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5760. Min Act: -0.0000

Data Index: 161607 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5963. Min Act: -0.0000

Data Index: 412616 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5538. Min Act: -0.0000

Data Index: 377939 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1559077 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.5516. Min Act: -0.0000

Data Index: 69501 (C4 (Web Text))

Max Activating Token Index: 948