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

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

Neuron 2013 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3821. Min Act: -0.0003

Data Index: 428699 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.3206. Min Act: -0.0003

Data Index: 548029 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2818. Min Act: -0.0003

Data Index: 547683 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2575. Min Act: -0.0003

Data Index: 921675 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2577. Min Act: -0.0003

Data Index: 848769 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2489. Min Act: -0.0003

Data Index: 1216009 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2432. Min Act: -0.0003

Data Index: 317188 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2339. Min Act: -0.0003

Data Index: 1009122 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2304. Min Act: -0.0003

Data Index: 1161669 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2111. Min Act: -0.0003

Data Index: 9506 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2356. Min Act: -0.0003

Data Index: 1084976 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2250. Min Act: -0.0003

Data Index: 945831 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2081. Min Act: -0.0003

Data Index: 1272964 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2169. Min Act: -0.0003

Data Index: 23077 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2065. Min Act: -0.0003

Data Index: 405428 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2143. Min Act: -0.0003

Data Index: 383961 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2194. Min Act: -0.0003

Data Index: 1069068 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2261. Min Act: -0.0003

Data Index: 658557 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2014. Min Act: -0.0003

Data Index: 1135106 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.3821. Min Range: -0.3821

Max Act: 0.2087. Min Act: -0.0003

Data Index: 408181 (C4 (Web Text))

Max Activating Token Index: 540