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

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

Neuron 1104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.9050. Min Act: -0.0001

Data Index: 300586 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1331085 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8060. Min Act: -0.0001

Data Index: 720335 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7909. Min Act: -0.0001

Data Index: 230549 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7626. Min Act: -0.0001

Data Index: 554196 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7238. Min Act: -0.0000

Data Index: 746738 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7460. Min Act: -0.0001

Data Index: 918251 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6978. Min Act: -0.0001

Data Index: 132902 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7370. Min Act: -0.0001

Data Index: 557507 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7986. Min Act: -0.0001

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6924. Min Act: -0.0000

Data Index: 648646 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7090. Min Act: -0.0000

Data Index: 365119 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6748. Min Act: -0.0001

Data Index: 573205 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6381. Min Act: -0.0001

Data Index: 307827 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7123. Min Act: -0.0001

Data Index: 64209 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1104184 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1247975 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6222. Min Act: -0.0001

Data Index: 67101 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6844. Min Act: -0.0001

Data Index: 1211084 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6435. Min Act: -0.0001

Data Index: 455467 (C4 (Web Text))

Max Activating Token Index: 569