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

Dataset: Open Web Text

Neuron 195 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: 4.6326. Min Range: -4.6326

Max Act: 4.6326. Min Act: -0.1700

Data Index: 2781025 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.6039. Min Act: -0.1700

Data Index: 1177794 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.6233. Min Act: -0.1700

Data Index: 238388 (Open Web Text)

Max Activating Token Index: 649

Text #3

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5840. Min Act: -0.1700

Data Index: 5602575 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5742. Min Act: -0.1700

Data Index: 7743376 (Open Web Text)

Max Activating Token Index: 538

Text #5

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5633. Min Act: -0.1700

Data Index: 874932 (Open Web Text)

Max Activating Token Index: 615

Text #6

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5646. Min Act: -0.1700

Data Index: 8338954 (Open Web Text)

Max Activating Token Index: 683

Text #7

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5756. Min Act: -0.1700

Data Index: 6569792 (Open Web Text)

Max Activating Token Index: 730

Text #8

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5706. Min Act: -0.1700

Data Index: 3069393 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5801. Min Act: -0.1700

Data Index: 6199324 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5742. Min Act: -0.1700

Data Index: 7594384 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5314. Min Act: -0.1700

Data Index: 6792893 (Open Web Text)

Max Activating Token Index: 362

Text #12

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5454. Min Act: -0.1700

Data Index: 4635146 (Open Web Text)

Max Activating Token Index: 559

Text #13

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5441. Min Act: -0.1700

Data Index: 4512913 (Open Web Text)

Max Activating Token Index: 627

Text #14

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5615. Min Act: -0.1700

Data Index: 3117048 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5321. Min Act: -0.1700

Data Index: 5061648 (Open Web Text)

Max Activating Token Index: 622

Text #16

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5489. Min Act: -0.1700

Data Index: 3597180 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5490. Min Act: -0.1700

Data Index: 471589 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5218. Min Act: -0.1700

Data Index: 6071791 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 4.6326. Min Range: -4.6326

Max Act: 4.5318. Min Act: -0.1700

Data Index: 6577266 (Open Web Text)

Max Activating Token Index: 825