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

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

Neuron 903 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: 0.2870. Min Range: -0.2870

Max Act: 0.2843. Min Act: -0.0003

Data Index: 863931 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2870. Min Act: -0.0003

Data Index: 28525 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2842. Min Act: -0.0003

Data Index: 30423 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2810. Min Act: -0.0003

Data Index: 807101 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2802. Min Act: -0.0003

Data Index: 327388 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2774. Min Act: -0.0003

Data Index: 904858 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2729. Min Act: -0.0003

Data Index: 8420 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2626. Min Act: -0.0003

Data Index: 786567 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2692. Min Act: -0.0003

Data Index: 981058 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2536. Min Act: -0.0003

Data Index: 1082736 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2622. Min Act: -0.0003

Data Index: 149397 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2527. Min Act: -0.0003

Data Index: 913045 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2494. Min Act: -0.0003

Data Index: 692716 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2614. Min Act: -0.0003

Data Index: 838551 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2524. Min Act: -0.0003

Data Index: 641976 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2562. Min Act: -0.0003

Data Index: 780317 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2447. Min Act: -0.0003

Data Index: 322180 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2449. Min Act: -0.0003

Data Index: 447182 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2441. Min Act: -0.0003

Data Index: 501567 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2612. Min Act: -0.0003

Data Index: 750139 (C4 (Web Text))

Max Activating Token Index: 718