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

Dataset: Open Web Text

Neuron 2698 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: 3.4664. Min Range: -3.4664

Max Act: 3.4541. Min Act: -0.1700

Data Index: 2131511 (Open Web Text)

Max Activating Token Index: 404

Text #1

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.4664. Min Act: -0.1700

Data Index: 2294243 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3644. Min Act: -0.1700

Data Index: 8755589 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3963. Min Act: -0.1700

Data Index: 3465 (Open Web Text)

Max Activating Token Index: 824

Text #4

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3562. Min Act: -0.1700

Data Index: 6031513 (Open Web Text)

Max Activating Token Index: 967

Text #5

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3675. Min Act: -0.1700

Data Index: 8699432 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3565. Min Act: -0.1700

Data Index: 2590176 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3547. Min Act: -0.1700

Data Index: 209022 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3695. Min Act: -0.1700

Data Index: 5301984 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3568. Min Act: -0.1700

Data Index: 6956176 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3675. Min Act: -0.1700

Data Index: 7320876 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3940. Min Act: -0.1700

Data Index: 5628212 (Open Web Text)

Max Activating Token Index: 649

Text #12

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3467. Min Act: -0.1700

Data Index: 3524278 (Open Web Text)

Max Activating Token Index: 262

Text #13

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3636. Min Act: -0.1700

Data Index: 7768708 (Open Web Text)

Max Activating Token Index: 709

Text #14

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3158. Min Act: -0.1700

Data Index: 5104244 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3513. Min Act: -0.1700

Data Index: 6726650 (Open Web Text)

Max Activating Token Index: 840

Text #16

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3448. Min Act: -0.1700

Data Index: 4805514 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3203. Min Act: -0.1700

Data Index: 6478557 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3282. Min Act: -0.1700

Data Index: 4620536 (Open Web Text)

Max Activating Token Index: 777

Text #19

Max Range: 3.4664. Min Range: -3.4664

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1550911 (Open Web Text)

Max Activating Token Index: 541