Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2699 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4187. Min Act: -0.0001

Data Index: 250807 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4263. Min Act: -0.0001

Data Index: 956308 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1238519 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4020. Min Act: -0.0001

Data Index: 510632 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4157. Min Act: -0.0001

Data Index: 234120 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3791. Min Act: -0.0001

Data Index: 833446 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4022. Min Act: -0.0001

Data Index: 31977 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4110. Min Act: -0.0001

Data Index: 286040 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3827. Min Act: -0.0001

Data Index: 796047 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3816. Min Act: -0.0001

Data Index: 950091 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3684. Min Act: -0.0001

Data Index: 114101 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3904. Min Act: -0.0001

Data Index: 692544 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3636. Min Act: -0.0001

Data Index: 530046 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3631. Min Act: -0.0001

Data Index: 744538 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3620. Min Act: -0.0001

Data Index: 1078305 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3680. Min Act: -0.0001

Data Index: 60813 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3664. Min Act: -0.0001

Data Index: 761474 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3873. Min Act: -0.0000

Data Index: 869581 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3648. Min Act: -0.0001

Data Index: 566209 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3502. Min Act: -0.0001

Data Index: 113863 (C4 (Web Text))

Max Activating Token Index: 534