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

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

Neuron 1457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0250. Min Range: -2.0250

Max Act: 2.0250. Min Act: -0.0000

Data Index: 869513 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8856. Min Act: -0.0000

Data Index: 452812 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.7949. Min Act: -0.0000

Data Index: 572610 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.8146. Min Act: -0.0000

Data Index: 1605071 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5857. Min Act: -0.0000

Data Index: 729502 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6395. Min Act: -0.0000

Data Index: 621172 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5768. Min Act: -0.0000

Data Index: 1383055 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6766. Min Act: -0.0000

Data Index: 1004831 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5785. Min Act: -0.0000

Data Index: 1300589 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5637. Min Act: -0.0000

Data Index: 669271 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5612. Min Act: -0.0000

Data Index: 356179 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1421901 (Python Code)

Max Activating Token Index: 897

Text #12

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5477. Min Act: -0.0000

Data Index: 934991 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.6315. Min Act: -0.0000

Data Index: 1157747 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5343. Min Act: -0.0000

Data Index: 848397 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.4923. Min Act: -0.0000

Data Index: 549295 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.4972. Min Act: -0.0000

Data Index: 382945 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1312719 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1501004 (Python Code)

Max Activating Token Index: 971

Text #19

Max Range: 2.0250. Min Range: -2.0250

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1171895 (C4 (Web Text))

Max Activating Token Index: 676