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

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

Neuron 4011 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: 1.8633. Min Range: -1.8633

Max Act: 1.8633. Min Act: -0.0002

Data Index: 247380 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.4653. Min Act: -0.0002

Data Index: 350851 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.4003. Min Act: -0.0002

Data Index: 151219 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.4005. Min Act: -0.0002

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3913. Min Act: -0.0002

Data Index: 216565 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.4050. Min Act: -0.0003

Data Index: 55885 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.4095. Min Act: -0.0002

Data Index: 1332432 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3626. Min Act: -0.0002

Data Index: 309436 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3283. Min Act: -0.0002

Data Index: 793956 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3227. Min Act: -0.0002

Data Index: 938926 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3541. Min Act: -0.0002

Data Index: 1192942 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3299. Min Act: -0.0002

Data Index: 999987 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3242. Min Act: -0.0002

Data Index: 633444 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3230. Min Act: -0.0002

Data Index: 1309576 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.2794. Min Act: -0.0002

Data Index: 115183 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.2804. Min Act: -0.0002

Data Index: 1258011 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.3133. Min Act: -0.0002

Data Index: 897768 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.2776. Min Act: -0.0002

Data Index: 1159919 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.2896. Min Act: -0.0002

Data Index: 302427 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.8633. Min Range: -1.8633

Max Act: 1.2817. Min Act: -0.0002

Data Index: 1236854 (C4 (Web Text))

Max Activating Token Index: 740