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

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

Neuron 403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.8940. Min Range: -6.8940

Max Act: 6.8940. Min Act: -0.0000

Data Index: 334522 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.9582. Min Act: -0.0000

Data Index: 563098 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.9162. Min Act: -0.0000

Data Index: 342534 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.8813. Min Act: -0.0000

Data Index: 253529 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.6303. Min Act: -0.0000

Data Index: 1195627 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 6.8940. Min Range: -6.8940

Max Act: 6.0038. Min Act: -0.0000

Data Index: 367098 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.6583. Min Act: -0.0000

Data Index: 1201671 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.6369. Min Act: -0.0000

Data Index: 153134 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.2219. Min Act: -0.0000

Data Index: 617575 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.3965. Min Act: -0.0000

Data Index: 787067 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.3850. Min Act: -0.0000

Data Index: 846545 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.4974. Min Act: -0.0000

Data Index: 1019514 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.4751. Min Act: -0.0000

Data Index: 148097 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.0595. Min Act: -0.0000

Data Index: 1085647 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.7485. Min Act: -0.0000

Data Index: 968849 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.2104. Min Act: -0.0000

Data Index: 1338623 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.1776. Min Act: -0.0000

Data Index: 713129 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 6.8940. Min Range: -6.8940

Max Act: 4.9913. Min Act: -0.0000

Data Index: 837963 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 6.8940. Min Range: -6.8940

Max Act: 4.8044. Min Act: -0.0000

Data Index: 628040 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 6.8940. Min Range: -6.8940

Max Act: 5.1245. Min Act: -0.0000

Data Index: 30864 (C4 (Web Text))

Max Activating Token Index: 608