Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1480 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.7652. Min Act: -0.0001

Data Index: 112336 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.4429. Min Act: -0.0001

Data Index: 925747 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.2827. Min Act: -0.0001

Data Index: 600403 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.2994. Min Act: -0.0001

Data Index: 158307 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.2967. Min Act: -0.0001

Data Index: 1201416 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.2523. Min Act: -0.0001

Data Index: 1155068 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.1871. Min Act: -0.0001

Data Index: 997013 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.9945. Min Act: -0.0001

Data Index: 252607 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.2891. Min Act: -0.0001

Data Index: 146147 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.1031. Min Act: -0.0001

Data Index: 967620 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.9352. Min Act: -0.0001

Data Index: 579918 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.8838. Min Act: -0.0001

Data Index: 745761 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.1348. Min Act: -0.0001

Data Index: 597819 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 3.7652. Min Range: -3.7652

Max Act: 3.0738. Min Act: -0.0001

Data Index: 548994 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.9389. Min Act: -0.0001

Data Index: 184521 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.9062. Min Act: -0.0001

Data Index: 325937 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.8975. Min Act: -0.0001

Data Index: 693517 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.8897. Min Act: -0.0001

Data Index: 486918 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.8809. Min Act: -0.0001

Data Index: 923874 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.7652. Min Range: -3.7652

Max Act: 2.7240. Min Act: -0.0001

Data Index: 852491 (C4 (Web Text))

Max Activating Token Index: 194