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

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

Neuron 3200 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2952. Min Act: -0.0002

Data Index: 1264565 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2901. Min Act: -0.0002

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2973. Min Act: -0.0002

Data Index: 914626 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2838. Min Act: -0.0002

Data Index: 1352633 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2778. Min Act: -0.0002

Data Index: 98277 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2626. Min Act: -0.0002

Data Index: 895578 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2819. Min Act: -0.0002

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2683. Min Act: -0.0003

Data Index: 724346 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2685. Min Act: -0.0002

Data Index: 658157 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2656. Min Act: -0.0002

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2578. Min Act: -0.0002

Data Index: 106657 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2620. Min Act: -0.0002

Data Index: 1173993 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2515. Min Act: -0.0002

Data Index: 1171833 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2537. Min Act: -0.0002

Data Index: 1174392 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2666. Min Act: -0.0002

Data Index: 562772 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2643. Min Act: -0.0003

Data Index: 1346928 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2452. Min Act: -0.0003

Data Index: 813526 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2524. Min Act: -0.0002

Data Index: 181564 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2531. Min Act: -0.0002

Data Index: 690956 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2516. Min Act: -0.0002

Data Index: 711497 (C4 (Web Text))

Max Activating Token Index: 470