Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.8382. Min Act: -0.1700

Data Index: 8397183 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.8499. Min Act: -0.1700

Data Index: 5746390 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7735. Min Act: -0.1700

Data Index: 6432860 (Open Web Text)

Max Activating Token Index: 694

Text #3

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7371. Min Act: -0.1700

Data Index: 6597660 (Open Web Text)

Max Activating Token Index: 72

Text #4

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7681. Min Act: -0.1700

Data Index: 5601965 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7343. Min Act: -0.1700

Data Index: 2819516 (Open Web Text)

Max Activating Token Index: 745

Text #6

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7104. Min Act: -0.1700

Data Index: 2081328 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7223. Min Act: -0.1700

Data Index: 3287911 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7418. Min Act: -0.1700

Data Index: 7201976 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7089. Min Act: -0.1700

Data Index: 3978211 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.6978. Min Act: -0.1700

Data Index: 7824003 (Open Web Text)

Max Activating Token Index: 1010

Text #11

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.6823. Min Act: -0.1700

Data Index: 7266804 (Open Web Text)

Max Activating Token Index: 642

Text #12

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7146. Min Act: -0.1700

Data Index: 2291724 (Open Web Text)

Max Activating Token Index: 848

Text #13

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7054. Min Act: -0.1700

Data Index: 939503 (Open Web Text)

Max Activating Token Index: 644

Text #14

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.6876. Min Act: -0.1700

Data Index: 8503307 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7547. Min Act: -0.1700

Data Index: 2453840 (Open Web Text)

Max Activating Token Index: 605

Text #16

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.7002. Min Act: -0.1700

Data Index: 6861499 (Open Web Text)

Max Activating Token Index: 806

Text #17

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.6659. Min Act: -0.1700

Data Index: 5280192 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.6828. Min Act: -0.1700

Data Index: 54357 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 4.8499. Min Range: -4.8499

Max Act: 4.6884. Min Act: -0.1700

Data Index: 5523103 (Open Web Text)

Max Activating Token Index: 89