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

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

Neuron 2944 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0224. Min Range: -1.0224

Max Act: 1.0224. Min Act: -0.0000

Data Index: 247173 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.9347. Min Act: -0.0000

Data Index: 751554 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.9154. Min Act: 0.0000

Data Index: 652350 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1259128 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.8234. Min Act: -0.0000

Data Index: 273816 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7949. Min Act: -0.0000

Data Index: 376003 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1167058 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7878. Min Act: -0.0000

Data Index: 744476 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7491. Min Act: -0.0000

Data Index: 593420 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1222651 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7335. Min Act: -0.0000

Data Index: 310323 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7555. Min Act: -0.0000

Data Index: 201723 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1054616 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1810 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.6936. Min Act: -0.0001

Data Index: 453252 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7283. Min Act: -0.0000

Data Index: 192003 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7261. Min Act: -0.0000

Data Index: 982140 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.6851. Min Act: -0.0001

Data Index: 246487 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1265681 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 1.0224. Min Range: -1.0224

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1298246 (C4 (Web Text))

Max Activating Token Index: 717