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

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

Neuron 5411 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.8749. Min Act: -0.0000

Data Index: 295188 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.8284. Min Act: -0.0000

Data Index: 8614 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.0844. Min Act: -0.0000

Data Index: 619224 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.0395. Min Act: -0.0000

Data Index: 585925 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.0147. Min Act: -0.0000

Data Index: 157735 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 2.8749. Min Range: -2.8749

Max Act: 2.3057. Min Act: -0.0000

Data Index: 124668 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.7820. Min Act: -0.0000

Data Index: 1121386 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.7620. Min Act: -0.0000

Data Index: 106078 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5154. Min Act: -0.0000

Data Index: 814586 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.3280. Min Act: -0.0000

Data Index: 505387 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1141807 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.4420. Min Act: -0.0000

Data Index: 646970 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.5086. Min Act: -0.0000

Data Index: 447358 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.3403. Min Act: -0.0000

Data Index: 475391 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.3836. Min Act: -0.0000

Data Index: 146189 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.4674. Min Act: -0.0000

Data Index: 602732 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.3188. Min Act: -0.0000

Data Index: 385308 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.2102. Min Act: -0.0000

Data Index: 491308 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.3050. Min Act: -0.0000

Data Index: 1080185 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 2.8749. Min Range: -2.8749

Max Act: 1.3593. Min Act: -0.0000

Data Index: 624757 (C4 (Web Text))

Max Activating Token Index: 918