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

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

Neuron 263 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5478. Min Act: -0.0001

Data Index: 625032 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5641. Min Act: -0.0001

Data Index: 470222 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5311. Min Act: -0.0001

Data Index: 720473 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5298. Min Act: -0.0001

Data Index: 476634 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5418. Min Act: -0.0001

Data Index: 469818 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4855. Min Act: -0.0001

Data Index: 678316 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4993. Min Act: -0.0001

Data Index: 384806 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4541. Min Act: -0.0001

Data Index: 1185857 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4521. Min Act: -0.0001

Data Index: 616095 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1279456 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4658. Min Act: -0.0001

Data Index: 1306582 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4303. Min Act: -0.0001

Data Index: 550197 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4338. Min Act: -0.0001

Data Index: 568077 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4578. Min Act: -0.0001

Data Index: 562646 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4428. Min Act: -0.0001

Data Index: 135864 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4691. Min Act: -0.0001

Data Index: 270457 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4264. Min Act: -0.0001

Data Index: 928566 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4096. Min Act: -0.0001

Data Index: 29758 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4003. Min Act: -0.0001

Data Index: 565107 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1358096 (C4 (Web Text))

Max Activating Token Index: 881