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

Dataset: Open Web Text

Neuron 2439 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: 4.6248. Min Range: -4.6248

Max Act: 4.6248. Min Act: -0.1700

Data Index: 60304 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.6228. Min Act: -0.1700

Data Index: 270284 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5802. Min Act: -0.1700

Data Index: 2928955 (Open Web Text)

Max Activating Token Index: 361

Text #3

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.6123. Min Act: -0.1700

Data Index: 6975186 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5965. Min Act: -0.1700

Data Index: 6940650 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.6126. Min Act: -0.1700

Data Index: 1492638 (Open Web Text)

Max Activating Token Index: 525

Text #6

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5789. Min Act: -0.1700

Data Index: 1811991 (Open Web Text)

Max Activating Token Index: 100

Text #7

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5811. Min Act: -0.1700

Data Index: 5104607 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5596. Min Act: -0.1700

Data Index: 1815934 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5610. Min Act: -0.1700

Data Index: 27315 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5923. Min Act: -0.1700

Data Index: 8208115 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.6059. Min Act: -0.1700

Data Index: 3246812 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5904. Min Act: -0.1700

Data Index: 1358649 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5786. Min Act: -0.1700

Data Index: 4971676 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5778. Min Act: -0.1700

Data Index: 6956589 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5478. Min Act: -0.1700

Data Index: 2731814 (Open Web Text)

Max Activating Token Index: 621

Text #16

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5896. Min Act: -0.1700

Data Index: 7019138 (Open Web Text)

Max Activating Token Index: 489

Text #17

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5605. Min Act: -0.1700

Data Index: 7970081 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5167. Min Act: -0.1700

Data Index: 2329656 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 4.6248. Min Range: -4.6248

Max Act: 4.5529. Min Act: -0.1700

Data Index: 4412240 (Open Web Text)

Max Activating Token Index: 619