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

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

Neuron 1010 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3910. Min Act: -0.0000

Data Index: 747348 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1184748 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4029. Min Act: -0.0000

Data Index: 277961 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4023. Min Act: -0.0000

Data Index: 374292 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1028327 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1142605 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3503. Min Act: -0.0000

Data Index: 285175 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3199. Min Act: -0.0000

Data Index: 397056 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3299. Min Act: -0.0000

Data Index: 57322 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3161. Min Act: -0.0000

Data Index: 676285 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3059. Min Act: -0.0000

Data Index: 118834 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1103858 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1306932 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3312. Min Act: -0.0000

Data Index: 328043 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1354505 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3303. Min Act: -0.0000

Data Index: 350844 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1074125 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1126057 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3161. Min Act: -0.0000

Data Index: 364448 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2986. Min Act: -0.0000

Data Index: 284176 (C4 (Web Text))

Max Activating Token Index: 147