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

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

Neuron 2125 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: 0.4493. Min Range: -0.4493

Max Act: 0.4493. Min Act: -0.0001

Data Index: 669646 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3810. Min Act: -0.0001

Data Index: 109658 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3778. Min Act: -0.0001

Data Index: 945732 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1082963 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1280900 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2986. Min Act: -0.0001

Data Index: 468840 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3104. Min Act: -0.0001

Data Index: 227847 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3318. Min Act: -0.0001

Data Index: 1349917 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3392. Min Act: -0.0001

Data Index: 733738 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3730. Min Act: -0.0001

Data Index: 1219838 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3248. Min Act: -0.0001

Data Index: 335130 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3566. Min Act: -0.0001

Data Index: 378494 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.3136. Min Act: -0.0001

Data Index: 975623 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2712. Min Act: -0.0001

Data Index: 81282 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2693. Min Act: -0.0001

Data Index: 490561 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2439. Min Act: -0.0001

Data Index: 356344 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2836. Min Act: -0.0001

Data Index: 18764 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1496572 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1013034 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.4493. Min Range: -0.4493

Max Act: 0.2686. Min Act: -0.0001

Data Index: 375119 (C4 (Web Text))

Max Activating Token Index: 846