Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3334 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.7120. Min Act: -0.0001

Data Index: 1172039 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6018. Min Act: -0.0001

Data Index: 576893 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5528. Min Act: -0.0001

Data Index: 264431 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5649. Min Act: -0.0001

Data Index: 50256 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5538. Min Act: -0.0001

Data Index: 1351819 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5218. Min Act: -0.0001

Data Index: 1305926 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5193. Min Act: -0.0001

Data Index: 117759 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4853. Min Act: -0.0001

Data Index: 1359793 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4898. Min Act: -0.0001

Data Index: 430464 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5280. Min Act: -0.0001

Data Index: 935541 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4684. Min Act: -0.0001

Data Index: 255597 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4922. Min Act: -0.0001

Data Index: 937026 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4546. Min Act: -0.0001

Data Index: 1051358 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4648. Min Act: -0.0001

Data Index: 948784 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4933. Min Act: -0.0001

Data Index: 314159 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5140. Min Act: -0.0001

Data Index: 3536 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4670. Min Act: -0.0001

Data Index: 864635 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5461. Min Act: -0.0001

Data Index: 1244540 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4934. Min Act: -0.0001

Data Index: 316626 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4932. Min Act: -0.0001

Data Index: 452366 (C4 (Web Text))

Max Activating Token Index: 450