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

Dataset: Open Web Text

Neuron 966 in Layer 6

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: 5.9393. Min Range: -5.9393

Max Act: 5.9393. Min Act: -0.1700

Data Index: 4415960 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.9309. Min Act: -0.1700

Data Index: 5877857 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8769. Min Act: -0.1700

Data Index: 4363097 (Open Web Text)

Max Activating Token Index: 945

Text #3

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.9005. Min Act: -0.1700

Data Index: 2890750 (Open Web Text)

Max Activating Token Index: 670

Text #4

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8691. Min Act: -0.1700

Data Index: 1517933 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8610. Min Act: -0.1700

Data Index: 5483159 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8595. Min Act: -0.1700

Data Index: 2501680 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8573. Min Act: -0.1700

Data Index: 1839283 (Open Web Text)

Max Activating Token Index: 975

Text #8

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8497. Min Act: -0.1700

Data Index: 1000498 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8570. Min Act: -0.1700

Data Index: 4624770 (Open Web Text)

Max Activating Token Index: 748

Text #10

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7858. Min Act: -0.1700

Data Index: 4089604 (Open Web Text)

Max Activating Token Index: 781

Text #11

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.8145. Min Act: -0.1700

Data Index: 6233953 (Open Web Text)

Max Activating Token Index: 560

Text #12

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7968. Min Act: -0.1700

Data Index: 2757611 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7588. Min Act: -0.1700

Data Index: 5919228 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7858. Min Act: -0.1700

Data Index: 1552428 (Open Web Text)

Max Activating Token Index: 742

Text #15

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7796. Min Act: -0.1700

Data Index: 6015279 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7729. Min Act: -0.1700

Data Index: 4496192 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7941. Min Act: -0.1700

Data Index: 7220303 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7723. Min Act: -0.1700

Data Index: 7571032 (Open Web Text)

Max Activating Token Index: 786

Text #19

Max Range: 5.9393. Min Range: -5.9393

Max Act: 5.7693. Min Act: -0.1700

Data Index: 3924517 (Open Web Text)

Max Activating Token Index: 958