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

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

Neuron 1421 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: 1.0760. Min Range: -1.0760

Max Act: 1.0760. Min Act: -0.0002

Data Index: 237233 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0432. Min Act: -0.0002

Data Index: 1032504 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0760. Min Act: -0.0002

Data Index: 860242 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.0760. Min Range: -1.0760

Max Act: 1.0265. Min Act: -0.0002

Data Index: 354513 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9967. Min Act: -0.0003

Data Index: 285923 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9820. Min Act: -0.0002

Data Index: 55370 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9742. Min Act: -0.0002

Data Index: 597437 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9405. Min Act: -0.0002

Data Index: 300549 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9212. Min Act: -0.0002

Data Index: 269117 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9265. Min Act: -0.0002

Data Index: 20907 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9486. Min Act: -0.0002

Data Index: 1016210 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9076. Min Act: -0.0003

Data Index: 458308 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9280. Min Act: -0.0002

Data Index: 100263 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8985. Min Act: -0.0002

Data Index: 948255 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9135. Min Act: -0.0002

Data Index: 218437 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.9125. Min Act: -0.0002

Data Index: 739028 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8972. Min Act: -0.0002

Data Index: 1351744 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8876. Min Act: -0.0002

Data Index: 163098 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8999. Min Act: -0.0002

Data Index: 1153885 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.0760. Min Range: -1.0760

Max Act: 0.8969. Min Act: -0.0002

Data Index: 56841 (C4 (Web Text))

Max Activating Token Index: 549