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

Dataset: Open Web Text

Neuron 1620 in Layer 4

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: 5.0486. Min Range: -5.0486

Max Act: 5.0359. Min Act: -0.1700

Data Index: 3178388 (Open Web Text)

Max Activating Token Index: 86

Text #1

Max Range: 5.0486. Min Range: -5.0486

Max Act: 5.0210. Min Act: -0.1700

Data Index: 8287080 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 5.0486. Min Range: -5.0486

Max Act: 5.0398. Min Act: -0.1700

Data Index: 274448 (Open Web Text)

Max Activating Token Index: 115

Text #3

Max Range: 5.0486. Min Range: -5.0486

Max Act: 5.0391. Min Act: -0.1700

Data Index: 1587617 (Open Web Text)

Max Activating Token Index: 530

Text #4

Max Range: 5.0486. Min Range: -5.0486

Max Act: 5.0486. Min Act: -0.1700

Data Index: 757224 (Open Web Text)

Max Activating Token Index: 350

Text #5

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9381. Min Act: -0.1700

Data Index: 6614766 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9523. Min Act: -0.1700

Data Index: 800512 (Open Web Text)

Max Activating Token Index: 583

Text #7

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9917. Min Act: -0.1700

Data Index: 8239403 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9344. Min Act: -0.1700

Data Index: 2490266 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9301. Min Act: -0.1700

Data Index: 6664831 (Open Web Text)

Max Activating Token Index: 512

Text #10

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9717. Min Act: -0.1700

Data Index: 6596521 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9318. Min Act: -0.1700

Data Index: 3395010 (Open Web Text)

Max Activating Token Index: 884

Text #12

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9388. Min Act: -0.1700

Data Index: 5225419 (Open Web Text)

Max Activating Token Index: 479

Text #13

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9177. Min Act: -0.1700

Data Index: 4779606 (Open Web Text)

Max Activating Token Index: 525

Text #14

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9532. Min Act: -0.1700

Data Index: 3258751 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9364. Min Act: -0.1700

Data Index: 95749 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.8960. Min Act: -0.1700

Data Index: 7143986 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.9037. Min Act: -0.1700

Data Index: 3360376 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.8913. Min Act: -0.1700

Data Index: 7938562 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 5.0486. Min Range: -5.0486

Max Act: 4.8931. Min Act: -0.1700

Data Index: 1070304 (Open Web Text)

Max Activating Token Index: 1023