Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3880 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.9520. Min Act: -0.0000

Data Index: 267649 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.5508. Min Act: -0.0000

Data Index: 28285 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.5174. Min Act: -0.0000

Data Index: 420455 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.0736. Min Act: -0.0000

Data Index: 53214 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.1609. Min Act: -0.0000

Data Index: 635397 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.9567. Min Act: -0.0000

Data Index: 778292 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.8558. Min Act: -0.0000

Data Index: 208081 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.9107. Min Act: -0.0000

Data Index: 1095330 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.7800. Min Act: -0.0000

Data Index: 54903 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 2.9520. Min Range: -2.9520

Max Act: 2.0029. Min Act: -0.0000

Data Index: 71558 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.8102. Min Act: -0.0000

Data Index: 525581 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.9184. Min Act: -0.0000

Data Index: 339885 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.6838. Min Act: -0.0000

Data Index: 862654 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.7824. Min Act: -0.0000

Data Index: 668499 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.6927. Min Act: -0.0000

Data Index: 708861 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.8963. Min Act: -0.0000

Data Index: 81020 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.7532. Min Act: -0.0000

Data Index: 217064 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.7474. Min Act: -0.0000

Data Index: 38140 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.7190. Min Act: -0.0000

Data Index: 951306 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.9520. Min Range: -2.9520

Max Act: 1.7057. Min Act: -0.0000

Data Index: 782930 (C4 (Web Text))

Max Activating Token Index: 649