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

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

Neuron 3272 in Layer 1

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: 2.2717. Min Range: -2.2717

Max Act: 2.2717. Min Act: -0.0002

Data Index: 366599 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 2.2717. Min Range: -2.2717

Max Act: 2.0399. Min Act: -0.0002

Data Index: 1266103 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 2.2717. Min Range: -2.2717

Max Act: 2.0337. Min Act: -0.0002

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9729. Min Act: -0.0002

Data Index: 795210 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9198. Min Act: -0.0002

Data Index: 551409 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8978. Min Act: -0.0002

Data Index: 411167 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9033. Min Act: -0.0002

Data Index: 1044446 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8865. Min Act: -0.0002

Data Index: 874157 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9270. Min Act: -0.0002

Data Index: 31320 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9450. Min Act: -0.0002

Data Index: 215884 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9313. Min Act: -0.0002

Data Index: 824168 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9184. Min Act: -0.0002

Data Index: 1329585 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.9090. Min Act: -0.0002

Data Index: 772226 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8133. Min Act: -0.0002

Data Index: 1221003 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8032. Min Act: -0.0002

Data Index: 615628 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8596. Min Act: -0.0002

Data Index: 727662 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8680. Min Act: -0.0002

Data Index: 1281375 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8316. Min Act: -0.0002

Data Index: 979895 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.8037. Min Act: -0.0002

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 2.2717. Min Range: -2.2717

Max Act: 1.7554. Min Act: -0.0002

Data Index: 1302251 (C4 (Web Text))

Max Activating Token Index: 382