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

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

Neuron 1104 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.7491. Min Act: -0.0000

Data Index: 1064944 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.6887. Min Act: -0.0000

Data Index: 1151759 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.6904. Min Act: -0.0000

Data Index: 632833 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1093030 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.5065. Min Act: -0.0000

Data Index: 173241 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.5037. Min Act: -0.0000

Data Index: 122541 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1295129 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4915. Min Act: -0.0000

Data Index: 122911 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4660. Min Act: -0.0000

Data Index: 707970 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4436. Min Act: -0.0000

Data Index: 986600 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.3727. Min Act: -0.0000

Data Index: 561624 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1180584 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.3647. Min Act: -0.0000

Data Index: 966424 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4143. Min Act: -0.0000

Data Index: 691380 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1244699 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.3263. Min Act: -0.0000

Data Index: 667028 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.3921. Min Act: -0.0000

Data Index: 730299 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.3763. Min Act: -0.0000

Data Index: 1181296 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.3617. Min Act: -0.0000

Data Index: 928953 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 1.7491. Min Range: -1.7491

Max Act: 1.4507. Min Act: -0.0000

Data Index: 54015 (C4 (Web Text))

Max Activating Token Index: 87