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

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

Neuron 2606 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: 1.7930. Min Range: -1.7930

Max Act: 1.7930. Min Act: -0.0001

Data Index: 1183622 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.6568. Min Act: -0.0001

Data Index: 1182125 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.7270. Min Act: -0.0001

Data Index: 853994 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.5534. Min Act: -0.0001

Data Index: 1168784 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4904. Min Act: -0.0000

Data Index: 923219 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.5545. Min Act: -0.0001

Data Index: 8770 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1121900 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3459. Min Act: -0.0001

Data Index: 782572 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4041. Min Act: -0.0001

Data Index: 1207425 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4059. Min Act: -0.0001

Data Index: 76223 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3663. Min Act: -0.0001

Data Index: 848486 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3719. Min Act: -0.0001

Data Index: 1248191 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.2814. Min Act: -0.0001

Data Index: 1228095 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4170. Min Act: -0.0001

Data Index: 273073 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.4009. Min Act: -0.0001

Data Index: 1059657 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.3784. Min Act: -0.0001

Data Index: 1115612 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.2216. Min Act: -0.0001

Data Index: 153455 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.2149. Min Act: -0.0001

Data Index: 167719 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.2648. Min Act: -0.0001

Data Index: 288107 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 1.7930. Min Range: -1.7930

Max Act: 1.1779. Min Act: -0.0000

Data Index: 14245 (C4 (Web Text))

Max Activating Token Index: 149