Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4705 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4553. Min Range: -2.4553

Max Act: 2.4553. Min Act: -0.0000

Data Index: 255244 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 2.4553. Min Range: -2.4553

Max Act: 2.0987. Min Act: -0.0000

Data Index: 965545 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 2.4553. Min Range: -2.4553

Max Act: 2.0101. Min Act: -0.0000

Data Index: 547837 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1216258 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1267358 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.7938. Min Act: -0.0000

Data Index: 118444 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.7370. Min Act: -0.0000

Data Index: 848474 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.4907. Min Act: -0.0000

Data Index: 14114 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.5676. Min Act: -0.0000

Data Index: 371793 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.6246. Min Act: -0.0000

Data Index: 264199 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1147518 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.6179. Min Act: -0.0000

Data Index: 82460 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1249668 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.5791. Min Act: -0.0000

Data Index: 500165 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.5570. Min Act: -0.0000

Data Index: 255130 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1274966 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1241056 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.4063. Min Act: -0.0000

Data Index: 244801 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1207591 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 2.4553. Min Range: -2.4553

Max Act: 1.4658. Min Act: -0.0000

Data Index: 44670 (C4 (Web Text))

Max Activating Token Index: 477