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

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

Neuron 925 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: 1.7247. Min Range: -1.7247

Max Act: 1.6866. Min Act: -0.0000

Data Index: 999806 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1197418 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.6632. Min Act: -0.0001

Data Index: 634215 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.6739. Min Act: -0.0000

Data Index: 364794 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.5907. Min Act: -0.0000

Data Index: 160803 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.4887. Min Act: -0.0000

Data Index: 246302 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.3959. Min Act: -0.0001

Data Index: 44250 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.7006. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.4253. Min Act: -0.0000

Data Index: 609510 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.3845. Min Act: -0.0000

Data Index: 140866 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.5401. Min Act: -0.0000

Data Index: 958943 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1221502 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.3348. Min Act: -0.0000

Data Index: 816020 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.4139. Min Act: -0.0000

Data Index: 1004342 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.4223. Min Act: -0.0000

Data Index: 762405 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.4804. Min Act: -0.0000

Data Index: 927092 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.2529. Min Act: -0.0000

Data Index: 636434 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1302580 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.4855. Min Act: -0.0000

Data Index: 482240 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 1.7247. Min Range: -1.7247

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1195568 (C4 (Web Text))

Max Activating Token Index: 771