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

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

Neuron 673 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2994. Min Act: -0.0000

Data Index: 533212 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.3089. Min Act: -0.0000

Data Index: 612221 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2452. Min Act: -0.0000

Data Index: 582943 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2241. Min Act: -0.0000

Data Index: 749603 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2228. Min Act: -0.0000

Data Index: 662672 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2287. Min Act: -0.0000

Data Index: 775962 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2137. Min Act: -0.0000

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2202. Min Act: -0.0000

Data Index: 51759 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2202. Min Act: -0.0000

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1316208 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1041938 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2001. Min Act: -0.0000

Data Index: 496670 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2083. Min Act: -0.0000

Data Index: 749497 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2026. Min Act: -0.0000

Data Index: 848780 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1988. Min Act: -0.0000

Data Index: 328923 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1336596 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2048. Min Act: -0.0000

Data Index: 927244 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1854. Min Act: -0.0000

Data Index: 593425 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1930. Min Act: -0.0000

Data Index: 728873 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1829. Min Act: -0.0000

Data Index: 983644 (C4 (Web Text))

Max Activating Token Index: 612