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

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

Neuron 3363 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6749. Min Act: -0.0000

Data Index: 834711 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5601. Min Act: -0.0000

Data Index: 714423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5721. Min Act: -0.0000

Data Index: 906777 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6103. Min Act: -0.0000

Data Index: 954630 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1295353 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5343. Min Act: -0.0000

Data Index: 408950 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1183092 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5529. Min Act: -0.0000

Data Index: 817443 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5100. Min Act: -0.0000

Data Index: 167763 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1268489 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5467. Min Act: -0.0000

Data Index: 416745 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4820. Min Act: -0.0000

Data Index: 788087 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5212. Min Act: -0.0000

Data Index: 858374 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4928. Min Act: -0.0000

Data Index: 290375 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1089512 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5495. Min Act: -0.0000

Data Index: 44885 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5169. Min Act: -0.0000

Data Index: 632830 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4952. Min Act: -0.0000

Data Index: 655962 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5437. Min Act: -0.0000

Data Index: 552233 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1324678 (C4 (Web Text))

Max Activating Token Index: 865