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

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

Neuron 278 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.4095. Min Act: -0.0000

Data Index: 321142 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.3377. Min Act: -0.0000

Data Index: 334498 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.1649. Min Act: -0.0000

Data Index: 107772 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.0936. Min Act: -0.0000

Data Index: 1065350 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.0170. Min Act: -0.0000

Data Index: 528231 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.9874. Min Act: 0.0000

Data Index: 406270 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.9771. Min Act: -0.0000

Data Index: 514232 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.4095. Min Range: -1.4095

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1151129 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.9487. Min Act: -0.0000

Data Index: 436130 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1161504 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.9053. Min Act: -0.0000

Data Index: 291335 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.8251. Min Act: -0.0000

Data Index: 932764 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.9872. Min Act: -0.0000

Data Index: 387631 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.8400. Min Act: -0.0000

Data Index: 330297 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.8486. Min Act: -0.0000

Data Index: 770431 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.8807. Min Act: -0.0000

Data Index: 374817 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1347596 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1075572 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.8363. Min Act: -0.0000

Data Index: 89262 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.4095. Min Range: -1.4095

Max Act: 0.8295. Min Act: -0.0000

Data Index: 349730 (C4 (Web Text))

Max Activating Token Index: 51