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

Dataset: Open Web Text

Neuron 1062 in Layer 1

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: 3.9122. Min Range: -3.9122

Max Act: 3.9122. Min Act: -0.1700

Data Index: 6379637 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.8759. Min Act: -0.1700

Data Index: 7198893 (Open Web Text)

Max Activating Token Index: 713

Text #2

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.8297. Min Act: -0.1700

Data Index: 8208748 (Open Web Text)

Max Activating Token Index: 879

Text #3

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.8219. Min Act: -0.1700

Data Index: 2702748 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.8101. Min Act: -0.1700

Data Index: 4443550 (Open Web Text)

Max Activating Token Index: 124

Text #5

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.7545. Min Act: -0.1700

Data Index: 3497672 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.7622. Min Act: -0.1700

Data Index: 6379636 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.7587. Min Act: -0.1700

Data Index: 3630754 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.7321. Min Act: -0.1700

Data Index: 3410922 (Open Web Text)

Max Activating Token Index: 187

Text #9

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6863. Min Act: -0.1700

Data Index: 6379639 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6862. Min Act: -0.1700

Data Index: 8377510 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6679. Min Act: -0.1700

Data Index: 5257253 (Open Web Text)

Max Activating Token Index: 408

Text #12

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6788. Min Act: -0.1700

Data Index: 919615 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6439. Min Act: -0.1700

Data Index: 2651342 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6351. Min Act: -0.1700

Data Index: 7426626 (Open Web Text)

Max Activating Token Index: 422

Text #15

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6259. Min Act: -0.1700

Data Index: 2665493 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6363. Min Act: -0.1700

Data Index: 617291 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6469. Min Act: -0.1700

Data Index: 6287100 (Open Web Text)

Max Activating Token Index: 466

Text #18

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6302. Min Act: -0.1700

Data Index: 7507825 (Open Web Text)

Max Activating Token Index: 98

Text #19

Max Range: 3.9122. Min Range: -3.9122

Max Act: 3.6451. Min Act: -0.1700

Data Index: 4654121 (Open Web Text)

Max Activating Token Index: 242