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

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

Neuron 3087 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.2633. Min Act: -0.0002

Data Index: 740248 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.2960. Min Act: -0.0002

Data Index: 409634 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.1081. Min Act: -0.0002

Data Index: 849020 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0980. Min Act: -0.0002

Data Index: 716463 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0522. Min Act: -0.0002

Data Index: 860466 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0807. Min Act: -0.0003

Data Index: 1108145 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.1554. Min Act: -0.0002

Data Index: 988917 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0381. Min Act: -0.0002

Data Index: 986613 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0064. Min Act: -0.0002

Data Index: 1179377 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0203. Min Act: -0.0003

Data Index: 1299844 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.9276. Min Act: -0.0002

Data Index: 671103 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0295. Min Act: -0.0002

Data Index: 591472 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 4.2960. Min Range: -4.2960

Max Act: 4.0367. Min Act: -0.0003

Data Index: 724528 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.9619. Min Act: -0.0002

Data Index: 718910 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.9332. Min Act: -0.0003

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.9561. Min Act: -0.0002

Data Index: 813055 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.8721. Min Act: -0.0002

Data Index: 1088532 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.8805. Min Act: -0.0003

Data Index: 666517 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.9584. Min Act: -0.0003

Data Index: 1133278 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 4.2960. Min Range: -4.2960

Max Act: 3.8044. Min Act: -0.0002

Data Index: 529806 (C4 (Web Text))

Max Activating Token Index: 482