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

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

Neuron 1035 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.5194. Min Act: -0.0000

Data Index: 522251 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.4494. Min Act: -0.0000

Data Index: 867022 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.4405. Min Act: -0.0000

Data Index: 529430 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.4525. Min Act: -0.0000

Data Index: 60920 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.4171. Min Act: -0.0000

Data Index: 836926 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1191554 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.4018. Min Act: -0.0000

Data Index: 571571 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.4087. Min Act: -0.0000

Data Index: 176644 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3843. Min Act: -0.0000

Data Index: 544975 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3847. Min Act: -0.0000

Data Index: 833416 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3802. Min Act: -0.0000

Data Index: 634271 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3342. Min Act: -0.0000

Data Index: 900819 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1127058 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3613. Min Act: -0.0000

Data Index: 602466 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3256. Min Act: -0.0000

Data Index: 489948 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3708. Min Act: -0.0000

Data Index: 882820 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3464. Min Act: -0.0000

Data Index: 112720 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3503. Min Act: -0.0000

Data Index: 366643 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3481. Min Act: -0.0000

Data Index: 33659 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.5194. Min Range: -0.5194

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1204661 (C4 (Web Text))

Max Activating Token Index: 656