Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1030 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0001

Data Index: 57125 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2926. Min Act: -0.0001

Data Index: 64973 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2820. Min Act: -0.0001

Data Index: 815184 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2929. Min Act: -0.0001

Data Index: 411982 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2846. Min Act: -0.0001

Data Index: 130195 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2720. Min Act: -0.0001

Data Index: 118272 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2620. Min Act: -0.0001

Data Index: 895997 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2622. Min Act: -0.0001

Data Index: 639007 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1013166 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2621. Min Act: -0.0001

Data Index: 296034 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2470. Min Act: -0.0001

Data Index: 254010 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2621. Min Act: -0.0001

Data Index: 442261 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1009712 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2514. Min Act: -0.0001

Data Index: 912837 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2586. Min Act: -0.0001

Data Index: 1937 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2484. Min Act: -0.0001

Data Index: 1299156 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2367. Min Act: -0.0001

Data Index: 170863 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2416. Min Act: -0.0001

Data Index: 876440 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1190423 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2488. Min Act: -0.0001

Data Index: 851197 (C4 (Web Text))

Max Activating Token Index: 1012