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

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

Neuron 3325 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: 2.2968. Min Range: -2.2968

Max Act: 2.2968. Min Act: -0.0000

Data Index: 466660 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 2.2968. Min Range: -2.2968

Max Act: 2.0019. Min Act: -0.0000

Data Index: 488718 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.8086. Min Act: -0.0000

Data Index: 1109245 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.9324. Min Act: -0.0000

Data Index: 429989 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.8261. Min Act: -0.0000

Data Index: 1187423 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.7180. Min Act: -0.0000

Data Index: 685989 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.8188. Min Act: -0.0000

Data Index: 634300 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.9143. Min Act: -0.0000

Data Index: 1319335 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.7184. Min Act: -0.0000

Data Index: 778902 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.9111. Min Act: -0.0000

Data Index: 1158994 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.7893. Min Act: -0.0000

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.6954. Min Act: -0.0000

Data Index: 1106764 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.6723. Min Act: -0.0000

Data Index: 543850 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.7413. Min Act: -0.0000

Data Index: 830683 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.7523. Min Act: -0.0000

Data Index: 883459 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.7641. Min Act: -0.0000

Data Index: 1222527 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.8339. Min Act: -0.0000

Data Index: 97407 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.6278. Min Act: -0.0000

Data Index: 796615 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.7190. Min Act: -0.0000

Data Index: 1004644 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 2.2968. Min Range: -2.2968

Max Act: 1.8026. Min Act: -0.0000

Data Index: 41466 (C4 (Web Text))

Max Activating Token Index: 816