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

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

Neuron 4645 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: 0.9397. Min Range: -0.9397

Max Act: 0.9270. Min Act: -0.0001

Data Index: 983742 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1029353 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8528. Min Act: -0.0001

Data Index: 702043 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8419. Min Act: -0.0000

Data Index: 270626 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.8167. Min Act: -0.0001

Data Index: 1111218 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6925. Min Act: -0.0001

Data Index: 383311 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7392. Min Act: -0.0001

Data Index: 335383 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7514. Min Act: -0.0001

Data Index: 971737 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7135. Min Act: -0.0001

Data Index: 950341 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1107415 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6575. Min Act: -0.0001

Data Index: 1248882 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6986. Min Act: -0.0001

Data Index: 441871 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6553. Min Act: -0.0001

Data Index: 524208 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6801. Min Act: -0.0001

Data Index: 997939 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6533. Min Act: -0.0001

Data Index: 1358439 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6831. Min Act: -0.0000

Data Index: 644128 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6546. Min Act: -0.0001

Data Index: 261240 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6009. Min Act: -0.0001

Data Index: 352545 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6280. Min Act: -0.0001

Data Index: 724198 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.9397. Min Range: -0.9397

Max Act: 0.6087. Min Act: -0.0001

Data Index: 1207227 (C4 (Web Text))

Max Activating Token Index: 402