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

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

Neuron 4798 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.6272. Min Act: -0.0001

Data Index: 799489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.4761. Min Act: -0.0001

Data Index: 43534 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.4306. Min Act: -0.0001

Data Index: 319463 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.4263. Min Act: -0.0001

Data Index: 316781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.4405. Min Act: -0.0001

Data Index: 651872 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.3624. Min Act: -0.0001

Data Index: 1252763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.3617. Min Act: -0.0001

Data Index: 879892 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.3848. Min Act: -0.0001

Data Index: 982598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.3303. Min Act: -0.0001

Data Index: 128949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.3022. Min Act: -0.0001

Data Index: 1266632 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2788. Min Act: -0.0001

Data Index: 553426 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2738. Min Act: -0.0001

Data Index: 766312 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2797. Min Act: -0.0001

Data Index: 1165931 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2595. Min Act: -0.0001

Data Index: 1244664 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2614. Min Act: -0.0001

Data Index: 1293368 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2625. Min Act: -0.0002

Data Index: 66419 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2602. Min Act: -0.0001

Data Index: 1216146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2709. Min Act: -0.0001

Data Index: 1095585 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2621. Min Act: -0.0001

Data Index: 1031320 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.6272. Min Range: -1.6272

Max Act: 1.2385. Min Act: -0.0002

Data Index: 690874 (C4 (Web Text))

Max Activating Token Index: 1023