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

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

Neuron 4858 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: 0.4121. Min Range: -0.4121

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1202203 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3921. Min Act: -0.0000

Data Index: 369426 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1039760 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3424. Min Act: -0.0000

Data Index: 136268 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3201. Min Act: -0.0000

Data Index: 342898 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1249191 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1231407 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3219. Min Act: -0.0000

Data Index: 184307 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3350. Min Act: -0.0000

Data Index: 824801 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3208. Min Act: -0.0000

Data Index: 795132 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3191. Min Act: -0.0000

Data Index: 745979 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3205. Min Act: -0.0000

Data Index: 364216 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1204551 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3034. Min Act: -0.0000

Data Index: 186062 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3130. Min Act: -0.0000

Data Index: 464766 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1067811 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3162. Min Act: -0.0000

Data Index: 905488 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2953. Min Act: -0.0000

Data Index: 515648 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1642594 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.4121. Min Range: -0.4121

Max Act: 0.2934. Min Act: -0.0000

Data Index: 726158 (C4 (Web Text))

Max Activating Token Index: 986