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

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

Neuron 3425 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: 1.3049. Min Range: -1.3049

Max Act: 1.3049. Min Act: -0.0001

Data Index: 418196 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9958. Min Act: -0.0001

Data Index: 1004522 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9558. Min Act: -0.0001

Data Index: 129968 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.8458. Min Act: -0.0001

Data Index: 1081622 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9248. Min Act: -0.0001

Data Index: 476626 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9210. Min Act: -0.0001

Data Index: 90455 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.8423. Min Act: -0.0001

Data Index: 588342 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9567. Min Act: -0.0001

Data Index: 650699 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7382. Min Act: -0.0001

Data Index: 226869 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.8112. Min Act: -0.0001

Data Index: 419698 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7860. Min Act: -0.0001

Data Index: 1304344 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7740. Min Act: -0.0001

Data Index: 174394 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.8107. Min Act: -0.0001

Data Index: 235750 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.8345. Min Act: -0.0001

Data Index: 811095 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7529. Min Act: -0.0001

Data Index: 1282951 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7693. Min Act: -0.0001

Data Index: 1230649 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1068564 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7753. Min Act: -0.0001

Data Index: 202023 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7376. Min Act: -0.0001

Data Index: 54107 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.7547. Min Act: -0.0001

Data Index: 273584 (C4 (Web Text))

Max Activating Token Index: 659