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

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

Neuron 2691 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3091. Min Range: -2.3091

Max Act: 2.3091. Min Act: -0.0000

Data Index: 1153705 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.9556. Min Act: -0.0000

Data Index: 101437 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.6991. Min Act: -0.0001

Data Index: 930495 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.6418. Min Act: -0.0001

Data Index: 542228 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.5155. Min Act: -0.0000

Data Index: 803951 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4862. Min Act: -0.0001

Data Index: 1139066 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1004057 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4714. Min Act: -0.0000

Data Index: 574229 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4771. Min Act: -0.0001

Data Index: 1622595 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4280. Min Act: -0.0001

Data Index: 303516 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4201. Min Act: -0.0001

Data Index: 1344629 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.5085. Min Act: -0.0000

Data Index: 1273953 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4586. Min Act: -0.0000

Data Index: 703999 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.3818. Min Act: -0.0000

Data Index: 1028742 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.4722. Min Act: -0.0000

Data Index: 594552 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.5099. Min Act: -0.0000

Data Index: 365649 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.5506. Min Act: -0.0001

Data Index: 749448 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.3879. Min Act: -0.0000

Data Index: 532289 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1128465 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 2.3091. Min Range: -2.3091

Max Act: 1.3934. Min Act: -0.0001

Data Index: 663754 (C4 (Web Text))

Max Activating Token Index: 745