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

Dataset: Open Web Text

Neuron 2632 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: 3.8072. Min Range: -3.8072

Max Act: 3.8072. Min Act: -0.1700

Data Index: 1636390 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.7443. Min Act: -0.1700

Data Index: 4045113 (Open Web Text)

Max Activating Token Index: 902

Text #2

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6834. Min Act: -0.1700

Data Index: 3606050 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6724. Min Act: -0.1700

Data Index: 3537176 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6973. Min Act: -0.1700

Data Index: 7288459 (Open Web Text)

Max Activating Token Index: 252

Text #5

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6759. Min Act: -0.1700

Data Index: 5338091 (Open Web Text)

Max Activating Token Index: 199

Text #6

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6631. Min Act: -0.1700

Data Index: 6616068 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6488. Min Act: -0.1700

Data Index: 7798316 (Open Web Text)

Max Activating Token Index: 863

Text #8

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6571. Min Act: -0.1700

Data Index: 2909832 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6443. Min Act: -0.1700

Data Index: 1379827 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6158. Min Act: -0.1700

Data Index: 7002658 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.5934. Min Act: -0.1700

Data Index: 5477424 (Open Web Text)

Max Activating Token Index: 785

Text #12

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6232. Min Act: -0.1700

Data Index: 6843518 (Open Web Text)

Max Activating Token Index: 392

Text #13

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.5840. Min Act: -0.1700

Data Index: 5801694 (Open Web Text)

Max Activating Token Index: 452

Text #14

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.6028. Min Act: -0.1700

Data Index: 8315676 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.5921. Min Act: -0.1700

Data Index: 4776578 (Open Web Text)

Max Activating Token Index: 783

Text #16

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.5896. Min Act: -0.1700

Data Index: 7784484 (Open Web Text)

Max Activating Token Index: 40

Text #17

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.5689. Min Act: -0.1700

Data Index: 3416613 (Open Web Text)

Max Activating Token Index: 566

Text #18

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.5753. Min Act: -0.1700

Data Index: 2819337 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 3.8072. Min Range: -3.8072

Max Act: 3.5635. Min Act: -0.1700

Data Index: 4489443 (Open Web Text)

Max Activating Token Index: 453