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

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

Neuron 1778 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.4150. Min Act: -0.0001

Data Index: 1236989 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.4454. Min Act: -0.0001

Data Index: 235826 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3947. Min Act: -0.0001

Data Index: 422329 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3394. Min Act: -0.0001

Data Index: 274511 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3400. Min Act: -0.0001

Data Index: 1241358 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3654. Min Act: -0.0001

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3405. Min Act: -0.0001

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3008. Min Act: -0.0001

Data Index: 421801 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3426. Min Act: -0.0001

Data Index: 490824 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1192033 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3063. Min Act: -0.0001

Data Index: 321 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3309. Min Act: -0.0001

Data Index: 1246997 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2989. Min Act: -0.0001

Data Index: 1102501 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3157. Min Act: -0.0001

Data Index: 699498 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1340916 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2867. Min Act: -0.0001

Data Index: 313498 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3025. Min Act: -0.0001

Data Index: 87402 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3024. Min Act: -0.0001

Data Index: 771306 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1139313 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3200. Min Act: -0.0001

Data Index: 353584 (C4 (Web Text))

Max Activating Token Index: 481