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

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

Neuron 4655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2067. Min Act: -0.0001

Data Index: 726663 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.3062. Min Act: -0.0001

Data Index: 882929 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.4026. Min Act: -0.0001

Data Index: 485683 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.4764. Min Act: -0.0001

Data Index: 619420 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2573. Min Act: -0.0001

Data Index: 165326 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2350. Min Act: -0.0001

Data Index: 162739 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2297. Min Act: -0.0001

Data Index: 134622 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2134. Min Act: -0.0001

Data Index: 1276841 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2049. Min Act: -0.0001

Data Index: 1099335 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.1784. Min Act: -0.0001

Data Index: 629811 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.1774. Min Act: -0.0001

Data Index: 1011620 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2489. Min Act: -0.0001

Data Index: 70842 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2303. Min Act: -0.0001

Data Index: 785424 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2320. Min Act: -0.0001

Data Index: 1046648 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.1800. Min Act: -0.0001

Data Index: 554309 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2656. Min Act: -0.0001

Data Index: 817714 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2018. Min Act: -0.0001

Data Index: 210113 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.1108. Min Act: -0.0001

Data Index: 189273 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.2825. Min Act: -0.0001

Data Index: 618053 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.4764. Min Range: -1.4764

Max Act: 1.1828. Min Act: -0.0001

Data Index: 944873 (C4 (Web Text))

Max Activating Token Index: 98