Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 851 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.3348. Min Act: -0.1700

Data Index: 1117629 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.2287. Min Act: -0.1700

Data Index: 211760 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1575. Min Act: -0.1700

Data Index: 519792 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1784. Min Act: -0.1700

Data Index: 1199985 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1477. Min Act: -0.1700

Data Index: 473215 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1070492 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1511. Min Act: -0.1700

Data Index: 281329 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1568. Min Act: -0.1700

Data Index: 125731 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1483. Min Act: -0.1700

Data Index: 52811 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1155. Min Act: -0.1700

Data Index: 797194 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1271. Min Act: -0.1700

Data Index: 537554 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1172. Min Act: -0.1700

Data Index: 439005 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.0983. Min Act: -0.1700

Data Index: 908123 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.0714. Min Act: -0.1700

Data Index: 944008 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1025. Min Act: -0.1700

Data Index: 943828 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1015. Min Act: -0.1700

Data Index: 723821 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.0728. Min Act: -0.1700

Data Index: 1314594 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.0783. Min Act: -0.1700

Data Index: 781835 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.0765. Min Act: -0.1700

Data Index: 349454 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.0496. Min Act: -0.1700

Data Index: 574148 (C4 (Web Text))

Max Activating Token Index: 830