Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1875 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.5050. Min Act: -0.0005

Data Index: 562103 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.4125. Min Act: -0.0005

Data Index: 1020530 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3244. Min Act: -0.0005

Data Index: 328065 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3366. Min Act: -0.0005

Data Index: 1097637 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3036. Min Act: -0.0005

Data Index: 688803 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2918. Min Act: -0.0005

Data Index: 948165 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.3016. Min Act: -0.0005

Data Index: 596283 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2656. Min Act: -0.0005

Data Index: 965627 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2587. Min Act: -0.0005

Data Index: 1029449 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2549. Min Act: -0.0005

Data Index: 951335 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2518. Min Act: -0.0005

Data Index: 741135 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2577. Min Act: -0.0005

Data Index: 548271 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2420. Min Act: -0.0005

Data Index: 551462 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2524. Min Act: -0.0005

Data Index: 452988 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2460. Min Act: -0.0005

Data Index: 694235 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2549. Min Act: -0.0005

Data Index: 920776 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2534. Min Act: -0.0005

Data Index: 1250335 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2365. Min Act: -0.0005

Data Index: 205337 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2589. Min Act: -0.0005

Data Index: 914814 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.5050. Min Range: -0.5050

Max Act: 0.2415. Min Act: -0.0005

Data Index: 1051267 (C4 (Web Text))

Max Activating Token Index: 670