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

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

Neuron 2914 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.4266. Min Act: -0.0000

Data Index: 274803 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3705. Min Act: -0.0001

Data Index: 389560 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3727. Min Act: -0.0001

Data Index: 870474 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3955. Min Act: -0.0001

Data Index: 585598 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1355594 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.3630. Min Act: -0.0001

Data Index: 28903 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1031123 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2728. Min Act: -0.0001

Data Index: 621919 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2790. Min Act: -0.0000

Data Index: 230740 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2334. Min Act: -0.0000

Data Index: 242051 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1443236 (Python Code)

Max Activating Token Index: 1004

Text #11

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2234. Min Act: -0.0000

Data Index: 491473 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2182. Min Act: -0.0001

Data Index: 148297 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1235784 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.1921. Min Act: -0.0001

Data Index: 581181 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.1906. Min Act: -0.0000

Data Index: 511671 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1204880 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.1814. Min Act: -0.0000

Data Index: 22137 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.1761. Min Act: -0.0000

Data Index: 769182 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.4266. Min Range: -0.4266

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1259761 (C4 (Web Text))

Max Activating Token Index: 173