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

Dataset: Open Web Text

Neuron 2641 in Layer 6

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: 5.6658. Min Range: -5.6658

Max Act: 5.6658. Min Act: -0.1700

Data Index: 1224805 (Open Web Text)

Max Activating Token Index: 386

Text #1

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4931. Min Act: -0.1700

Data Index: 1160084 (Open Web Text)

Max Activating Token Index: 832

Text #2

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4796. Min Act: -0.1700

Data Index: 3352282 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4667. Min Act: -0.1700

Data Index: 1117293 (Open Web Text)

Max Activating Token Index: 597

Text #4

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4415. Min Act: -0.1700

Data Index: 6095459 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4234. Min Act: -0.1700

Data Index: 4927762 (Open Web Text)

Max Activating Token Index: 670

Text #6

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4445. Min Act: -0.1700

Data Index: 3561528 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4473. Min Act: -0.1700

Data Index: 8108560 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4410. Min Act: -0.1700

Data Index: 7238132 (Open Web Text)

Max Activating Token Index: 316

Text #9

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4437. Min Act: -0.1700

Data Index: 194385 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4138. Min Act: -0.1700

Data Index: 700081 (Open Web Text)

Max Activating Token Index: 835

Text #11

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4185. Min Act: -0.1700

Data Index: 1691071 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4536. Min Act: -0.1700

Data Index: 2059049 (Open Web Text)

Max Activating Token Index: 663

Text #13

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.3894. Min Act: -0.1700

Data Index: 7440317 (Open Web Text)

Max Activating Token Index: 285

Text #14

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4062. Min Act: -0.1700

Data Index: 8258413 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.4033. Min Act: -0.1700

Data Index: 126061 (Open Web Text)

Max Activating Token Index: 56

Text #16

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.3756. Min Act: -0.1700

Data Index: 1369755 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.3458. Min Act: -0.1700

Data Index: 6784492 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.3512. Min Act: -0.1700

Data Index: 5566248 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 5.6658. Min Range: -5.6658

Max Act: 5.3813. Min Act: -0.1700

Data Index: 8254500 (Open Web Text)

Max Activating Token Index: 693