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

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

Neuron 2384 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.3974. Min Act: -0.0000

Data Index: 1108482 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.2584. Min Act: -0.0000

Data Index: 921840 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.3267. Min Act: -0.0000

Data Index: 239956 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.3082. Min Act: -0.0000

Data Index: 833485 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1290949 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.3068. Min Act: -0.0000

Data Index: 552627 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.1304. Min Act: -0.0000

Data Index: 455554 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.1314. Min Act: -0.0000

Data Index: 668372 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.0701. Min Act: -0.0000

Data Index: 200810 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1166249 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.1347. Min Act: -0.0000

Data Index: 995833 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.0542. Min Act: -0.0000

Data Index: 386461 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1126179 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.0452. Min Act: -0.0000

Data Index: 116837 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.1179. Min Act: -0.0000

Data Index: 925870 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 1.3974. Min Range: -1.3974

Max Act: 1.0112. Min Act: -0.0000

Data Index: 604957 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.3974. Min Range: -1.3974

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1347735 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 1.3974. Min Range: -1.3974

Max Act: 0.9885. Min Act: -0.0000

Data Index: 203733 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.3974. Min Range: -1.3974

Max Act: 0.9734. Min Act: -0.0000

Data Index: 753492 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.3974. Min Range: -1.3974

Max Act: 0.9558. Min Act: -0.0000

Data Index: 190220 (C4 (Web Text))

Max Activating Token Index: 669