Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5537 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1434209 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1760 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3575. Min Act: -0.0000

Data Index: 840370 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1501136 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4138. Min Act: -0.0000

Data Index: 949599 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4283. Min Act: -0.0000

Data Index: 653338 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1512392 (Python Code)

Max Activating Token Index: 517

Text #7

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3080. Min Act: -0.0000

Data Index: 191511 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3904. Min Act: -0.0000

Data Index: 581600 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3130. Min Act: -0.0000

Data Index: 103799 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3858. Min Act: -0.0000

Data Index: 850023 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3758. Min Act: -0.0000

Data Index: 626336 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3696. Min Act: -0.0000

Data Index: 698566 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1088122 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2992. Min Act: -0.0000

Data Index: 367298 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2586. Min Act: -0.0000

Data Index: 1589944 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2828. Min Act: -0.0000

Data Index: 100019 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2809. Min Act: -0.0000

Data Index: 503029 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2407. Min Act: -0.0000

Data Index: 961970 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1202197 (C4 (Web Text))

Max Activating Token Index: 46