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

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

Neuron 5680 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: 2.0082. Min Range: -2.0082

Max Act: 2.0082. Min Act: -0.0002

Data Index: 850169 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.9772. Min Act: -0.0002

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.9153. Min Act: -0.0002

Data Index: 154565 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8825. Min Act: -0.0002

Data Index: 1073692 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.9297. Min Act: -0.0002

Data Index: 28745 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8670. Min Act: -0.0002

Data Index: 436663 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8391. Min Act: -0.0002

Data Index: 704736 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8445. Min Act: -0.0002

Data Index: 924294 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8328. Min Act: -0.0002

Data Index: 1110853 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8261. Min Act: -0.0002

Data Index: 998898 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.7999. Min Act: -0.0002

Data Index: 60118 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8561. Min Act: -0.0002

Data Index: 672685 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.7787. Min Act: -0.0002

Data Index: 1208049 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.7802. Min Act: -0.0002

Data Index: 585943 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8211. Min Act: -0.0002

Data Index: 469625 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8092. Min Act: -0.0002

Data Index: 472672 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.7986. Min Act: -0.0002

Data Index: 73295 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.7821. Min Act: -0.0002

Data Index: 407570 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.7572. Min Act: -0.0002

Data Index: 489397 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 2.0082. Min Range: -2.0082

Max Act: 1.8337. Min Act: -0.0002

Data Index: 939790 (C4 (Web Text))

Max Activating Token Index: 523