Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3657. Min Act: -0.0001

Data Index: 138006 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3490. Min Act: -0.0000

Data Index: 944454 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3485. Min Act: -0.0000

Data Index: 905645 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3248. Min Act: -0.0000

Data Index: 390920 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3343. Min Act: -0.0001

Data Index: 311159 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3317. Min Act: -0.0000

Data Index: 28084 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3346. Min Act: -0.0001

Data Index: 518010 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3275. Min Act: -0.0001

Data Index: 1055531 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1289478 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3186. Min Act: -0.0001

Data Index: 1147018 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3175. Min Act: -0.0000

Data Index: 383174 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2981. Min Act: -0.0001

Data Index: 603289 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2863. Min Act: -0.0000

Data Index: 28845 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.3059. Min Act: -0.0000

Data Index: 508656 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2924. Min Act: -0.0000

Data Index: 806451 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2991. Min Act: -0.0000

Data Index: 109407 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2991. Min Act: -0.0000

Data Index: 351772 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1267614 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2761. Min Act: -0.0000

Data Index: 177557 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.3657. Min Range: -0.3657

Max Act: 0.2868. Min Act: -0.0000

Data Index: 849116 (C4 (Web Text))

Max Activating Token Index: 599