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

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

Neuron 742 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1074616 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5660. Min Act: -0.0000

Data Index: 355183 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5419. Min Act: -0.0000

Data Index: 63057 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4957. Min Act: -0.0000

Data Index: 525069 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4876. Min Act: -0.0000

Data Index: 99403 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4730. Min Act: -0.0000

Data Index: 73638 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4863. Min Act: -0.0000

Data Index: 893701 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5003. Min Act: -0.0000

Data Index: 668401 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4732. Min Act: -0.0000

Data Index: 263711 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4889. Min Act: -0.0000

Data Index: 841191 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4602. Min Act: -0.0000

Data Index: 118784 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4641. Min Act: -0.0000

Data Index: 990925 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4236. Min Act: -0.0000

Data Index: 579709 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4174. Min Act: -0.0000

Data Index: 422089 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4451. Min Act: -0.0000

Data Index: 51715 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4461. Min Act: -0.0000

Data Index: 115270 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4231. Min Act: -0.0000

Data Index: 416940 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4360. Min Act: -0.0000

Data Index: 643059 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1025912 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4157. Min Act: -0.0000

Data Index: 885837 (C4 (Web Text))

Max Activating Token Index: 342