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

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

Neuron 5320 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.8000. Min Act: -0.0000

Data Index: 714615 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6409. Min Act: -0.0000

Data Index: 802385 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5737. Min Act: -0.0000

Data Index: 765807 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5422. Min Act: -0.0000

Data Index: 51941 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5531. Min Act: -0.0000

Data Index: 160869 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.5266. Min Act: -0.0000

Data Index: 331620 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1358233 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4527. Min Act: -0.0000

Data Index: 613250 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1087089 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4742. Min Act: -0.0000

Data Index: 569528 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1237938 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.6035. Min Act: -0.0000

Data Index: 158105 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4971. Min Act: -0.0000

Data Index: 767711 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1250152 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4885. Min Act: -0.0000

Data Index: 445510 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4480. Min Act: -0.0000

Data Index: 201864 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4575. Min Act: -0.0000

Data Index: 495109 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4474. Min Act: -0.0000

Data Index: 238745 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.3967. Min Act: -0.0000

Data Index: 781423 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.8000. Min Range: -0.8000

Max Act: 0.4517. Min Act: -0.0000

Data Index: 621796 (C4 (Web Text))

Max Activating Token Index: 849