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

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

Neuron 2527 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3332. Min Range: -1.3332

Max Act: 1.3332. Min Act: -0.0001

Data Index: 615801 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.3332. Min Range: -1.3332

Max Act: 1.1582. Min Act: -0.0001

Data Index: 209211 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 1.3332. Min Range: -1.3332

Max Act: 1.1443. Min Act: -0.0001

Data Index: 58820 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 1.3332. Min Range: -1.3332

Max Act: 1.0831. Min Act: -0.0001

Data Index: 639337 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9850. Min Act: -0.0001

Data Index: 25645 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.3332. Min Range: -1.3332

Max Act: 1.0070. Min Act: -0.0001

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 1.3332. Min Range: -1.3332

Max Act: 1.0160. Min Act: -0.0001

Data Index: 415125 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9981. Min Act: -0.0001

Data Index: 284648 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 1.3332. Min Range: -1.3332

Max Act: 1.0115. Min Act: -0.0001

Data Index: 297712 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9756. Min Act: -0.0001

Data Index: 739909 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9489. Min Act: -0.0001

Data Index: 995282 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9877. Min Act: -0.0001

Data Index: 1003093 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9130. Min Act: -0.0001

Data Index: 423479 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9587. Min Act: -0.0001

Data Index: 93925 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9570. Min Act: -0.0001

Data Index: 246457 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.8779. Min Act: -0.0001

Data Index: 169735 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9521. Min Act: -0.0001

Data Index: 1293349 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9280. Min Act: -0.0001

Data Index: 155718 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.9180. Min Act: -0.0001

Data Index: 10592 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 1.3332. Min Range: -1.3332

Max Act: 0.8788. Min Act: -0.0001

Data Index: 778064 (C4 (Web Text))

Max Activating Token Index: 863