Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.3428. Min Act: -0.0003

Data Index: 1043854 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.3289. Min Act: -0.0003

Data Index: 371243 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.3093. Min Act: -0.0003

Data Index: 595889 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2983. Min Act: -0.0003

Data Index: 313357 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2969. Min Act: -0.0003

Data Index: 224700 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2946. Min Act: -0.0003

Data Index: 471160 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.3138. Min Act: -0.0003

Data Index: 796446 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2803. Min Act: -0.0003

Data Index: 876777 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2918. Min Act: -0.0003

Data Index: 39962 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2868. Min Act: -0.0003

Data Index: 142841 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2659. Min Act: -0.0003

Data Index: 1313036 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2611. Min Act: -0.0003

Data Index: 625749 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2674. Min Act: -0.0003

Data Index: 782866 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2523. Min Act: -0.0003

Data Index: 678811 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2787. Min Act: -0.0003

Data Index: 716846 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2522. Min Act: -0.0003

Data Index: 1234737 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2607. Min Act: -0.0003

Data Index: 407429 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2879. Min Act: -0.0003

Data Index: 478450 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2385. Min Act: -0.0003

Data Index: 24501 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2562. Min Act: -0.0003

Data Index: 1128355 (C4 (Web Text))

Max Activating Token Index: 1014