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

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

Neuron 1480 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.7840. Min Act: -0.0000

Data Index: 339364 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.7513. Min Act: -0.0000

Data Index: 478678 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.6397. Min Act: -0.0000

Data Index: 343264 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.5782. Min Act: -0.0000

Data Index: 105946 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.6167. Min Act: -0.0000

Data Index: 186524 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.4509. Min Act: -0.0000

Data Index: 706135 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.4842. Min Act: -0.0000

Data Index: 1236912 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3904. Min Act: -0.0000

Data Index: 487740 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3061. Min Act: -0.0000

Data Index: 334254 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3690. Min Act: -0.0000

Data Index: 808207 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1013427 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.2436. Min Act: -0.0000

Data Index: 78447 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3151. Min Act: -0.0000

Data Index: 1372718 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3016. Min Act: -0.0000

Data Index: 15254 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1166972 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3015. Min Act: -0.0000

Data Index: 918791 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3907. Min Act: -0.0000

Data Index: 400963 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3072. Min Act: -0.0000

Data Index: 113586 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.3187. Min Act: -0.0000

Data Index: 407504 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.7840. Min Range: -1.7840

Max Act: 1.2979. Min Act: -0.0000

Data Index: 319478 (C4 (Web Text))

Max Activating Token Index: 736