Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1175 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2587. Min Act: -0.0000

Data Index: 330498 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2435. Min Act: -0.0001

Data Index: 981931 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2140. Min Act: -0.0001

Data Index: 80146 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2188. Min Act: -0.0001

Data Index: 434287 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2170. Min Act: -0.0001

Data Index: 240179 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1342937 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2025. Min Act: -0.0000

Data Index: 105413 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1958. Min Act: -0.0001

Data Index: 954618 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1338297 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1917. Min Act: -0.0001

Data Index: 357438 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1874. Min Act: -0.0001

Data Index: 660613 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1280277 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1918. Min Act: -0.0001

Data Index: 909834 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1037479 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1799. Min Act: -0.0001

Data Index: 978962 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1726. Min Act: -0.0001

Data Index: 938006 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1810. Min Act: -0.0001

Data Index: 1095269 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1748. Min Act: -0.0001

Data Index: 51586 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1289944 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1151514 (C4 (Web Text))

Max Activating Token Index: 823