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

Dataset: Open Web Text

Neuron 79 in Layer 5

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: 3.5220. Min Range: -3.5220

Max Act: 3.5030. Min Act: -0.1700

Data Index: 3972701 (Open Web Text)

Max Activating Token Index: 580

Text #1

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.5220. Min Act: -0.1700

Data Index: 6523154 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4999. Min Act: -0.1700

Data Index: 5756614 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4691. Min Act: -0.1700

Data Index: 8208444 (Open Web Text)

Max Activating Token Index: 424

Text #4

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4701. Min Act: -0.1700

Data Index: 2095878 (Open Web Text)

Max Activating Token Index: 414

Text #5

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4652. Min Act: -0.1700

Data Index: 7560621 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1478259 (Open Web Text)

Max Activating Token Index: 316

Text #7

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4559. Min Act: -0.1700

Data Index: 3691421 (Open Web Text)

Max Activating Token Index: 696

Text #8

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4448. Min Act: -0.1700

Data Index: 7832800 (Open Web Text)

Max Activating Token Index: 914

Text #9

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4321. Min Act: -0.1700

Data Index: 1793497 (Open Web Text)

Max Activating Token Index: 457

Text #10

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4333. Min Act: -0.1700

Data Index: 7192512 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4462. Min Act: -0.1700

Data Index: 4745531 (Open Web Text)

Max Activating Token Index: 633

Text #12

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4540. Min Act: -0.1700

Data Index: 5838876 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4427. Min Act: -0.1700

Data Index: 6790974 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4185. Min Act: -0.1700

Data Index: 4745524 (Open Web Text)

Max Activating Token Index: 721

Text #15

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4275. Min Act: -0.1700

Data Index: 2447524 (Open Web Text)

Max Activating Token Index: 348

Text #16

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4197. Min Act: -0.1700

Data Index: 7582754 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4273. Min Act: -0.1700

Data Index: 6824195 (Open Web Text)

Max Activating Token Index: 762

Text #18

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4315. Min Act: -0.1700

Data Index: 7698953 (Open Web Text)

Max Activating Token Index: 597

Text #19

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4466. Min Act: -0.1700

Data Index: 7809021 (Open Web Text)

Max Activating Token Index: 588