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

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

Neuron 4132 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: 0.6547. Min Range: -0.6547

Max Act: 0.6547. Min Act: -0.0000

Data Index: 87969 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.5911. Min Act: -0.0000

Data Index: 25623 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.5285. Min Act: -0.0000

Data Index: 56662 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.5254. Min Act: -0.0000

Data Index: 738888 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1274129 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.5061. Min Act: -0.0000

Data Index: 140746 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4870. Min Act: -0.0000

Data Index: 620999 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1189139 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4905. Min Act: -0.0000

Data Index: 960734 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4718. Min Act: -0.0001

Data Index: 1276257 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4820. Min Act: -0.0000

Data Index: 146924 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4631. Min Act: -0.0000

Data Index: 813237 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4550. Min Act: -0.0000

Data Index: 468550 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1014130 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4949. Min Act: -0.0000

Data Index: 44090 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1049159 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4422. Min Act: -0.0000

Data Index: 665324 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4366. Min Act: -0.0000

Data Index: 249559 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4570. Min Act: -0.0000

Data Index: 281132 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.6547. Min Range: -0.6547

Max Act: 0.4388. Min Act: -0.0000

Data Index: 161973 (C4 (Web Text))

Max Activating Token Index: 992