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

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

Neuron 2184 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: 2.7740. Min Range: -2.7740

Max Act: 2.7740. Min Act: -0.0000

Data Index: 1103387 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2339. Min Act: -0.0000

Data Index: 12271 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3437. Min Act: -0.0000

Data Index: 857785 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.6079. Min Act: -0.0000

Data Index: 1074713 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3330. Min Act: -0.0000

Data Index: 529331 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2034. Min Act: -0.0000

Data Index: 526584 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2692. Min Act: -0.0000

Data Index: 208930 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1429. Min Act: -0.0000

Data Index: 1164644 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3670. Min Act: -0.0000

Data Index: 1238409 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2246. Min Act: -0.0000

Data Index: 1178419 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2993. Min Act: -0.0000

Data Index: 674010 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1574. Min Act: -0.0000

Data Index: 993883 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2793. Min Act: -0.0000

Data Index: 1081527 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1365. Min Act: -0.0000

Data Index: 367085 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1519. Min Act: -0.0000

Data Index: 1219375 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 2.7740. Min Range: -2.7740

Max Act: 1.9985. Min Act: -0.0000

Data Index: 1353988 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1078. Min Act: -0.0000

Data Index: 193078 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.0980. Min Act: -0.0000

Data Index: 419200 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 2.7740. Min Range: -2.7740

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1015636 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1935. Min Act: -0.0000

Data Index: 1135443 (C4 (Web Text))

Max Activating Token Index: 446