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

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

Neuron 895 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8827. Min Range: -5.8827

Max Act: 5.8827. Min Act: -0.0000

Data Index: 1255968 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 5.8827. Min Range: -5.8827

Max Act: 4.4377. Min Act: -0.0000

Data Index: 493851 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 5.8827. Min Range: -5.8827

Max Act: 2.7704. Min Act: -0.0000

Data Index: 7188 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 5.8827. Min Range: -5.8827

Max Act: 2.0703. Min Act: -0.0000

Data Index: 52756 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 5.8827. Min Range: -5.8827

Max Act: 2.2295. Min Act: -0.0000

Data Index: 1046754 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.9774. Min Act: -0.0000

Data Index: 893974 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.9563. Min Act: -0.0000

Data Index: 44200 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.8082. Min Act: -0.0000

Data Index: 855647 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.6975. Min Act: -0.0000

Data Index: 929821 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.7187. Min Act: -0.0000

Data Index: 88745 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.7157. Min Act: -0.0000

Data Index: 1039693 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.7568. Min Act: -0.0000

Data Index: 139458 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1028954 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.5343. Min Act: -0.0000

Data Index: 594120 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.6218. Min Act: -0.0000

Data Index: 731125 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.7071. Min Act: -0.0000

Data Index: 202928 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.5949. Min Act: -0.0000

Data Index: 1264362 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.5185. Min Act: -0.0000

Data Index: 1256038 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.5923. Min Act: -0.0000

Data Index: 62063 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 5.8827. Min Range: -5.8827

Max Act: 1.5926. Min Act: -0.0000

Data Index: 212417 (C4 (Web Text))

Max Activating Token Index: 411