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

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

Neuron 1205 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7983. Min Act: -0.0000

Data Index: 760435 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7460. Min Act: -0.0000

Data Index: 378157 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1266538 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1290956 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7630. Min Act: -0.0000

Data Index: 289727 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1024596 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7279. Min Act: -0.0000

Data Index: 420122 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6501. Min Act: -0.0000

Data Index: 719480 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6991. Min Act: -0.0000

Data Index: 404267 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6654. Min Act: -0.0000

Data Index: 744692 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6519. Min Act: -0.0000

Data Index: 630457 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6177. Min Act: -0.0000

Data Index: 11919 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6629. Min Act: -0.0000

Data Index: 812124 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6283. Min Act: -0.0000

Data Index: 266949 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1178298 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5984. Min Act: -0.0000

Data Index: 194636 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5791. Min Act: -0.0000

Data Index: 500004 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6082. Min Act: -0.0000

Data Index: 336301 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6406. Min Act: -0.0000

Data Index: 693702 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6040. Min Act: -0.0000

Data Index: 208181 (C4 (Web Text))

Max Activating Token Index: 435