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

Dataset: Open Web Text

Neuron 2121 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: 7.4550. Min Range: -7.4550

Max Act: 7.4550. Min Act: -0.1700

Data Index: 2984505 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.3294. Min Act: -0.1700

Data Index: 455549 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.2372. Min Act: -0.1700

Data Index: 5496051 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.2292. Min Act: -0.1700

Data Index: 2134350 (Open Web Text)

Max Activating Token Index: 992

Text #4

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.1690. Min Act: -0.1700

Data Index: 8685772 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.1606. Min Act: -0.1700

Data Index: 192734 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.1317. Min Act: -0.1700

Data Index: 7978974 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.0480. Min Act: -0.1700

Data Index: 6305652 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.0789. Min Act: -0.1700

Data Index: 8292345 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.0854. Min Act: -0.1700

Data Index: 3468204 (Open Web Text)

Max Activating Token Index: 615

Text #10

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.0508. Min Act: -0.1700

Data Index: 5018866 (Open Web Text)

Max Activating Token Index: 699

Text #11

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.0271. Min Act: -0.1700

Data Index: 2574728 (Open Web Text)

Max Activating Token Index: 775

Text #12

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.0051. Min Act: -0.1700

Data Index: 7014918 (Open Web Text)

Max Activating Token Index: 984

Text #13

Max Range: 7.4550. Min Range: -7.4550

Max Act: 7.0383. Min Act: -0.1700

Data Index: 8732842 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 7.4550. Min Range: -7.4550

Max Act: 6.9530. Min Act: -0.1700

Data Index: 7910628 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 7.4550. Min Range: -7.4550

Max Act: 6.9579. Min Act: -0.1700

Data Index: 8820457 (Open Web Text)

Max Activating Token Index: 922

Text #16

Max Range: 7.4550. Min Range: -7.4550

Max Act: 6.9587. Min Act: -0.1700

Data Index: 1951717 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 7.4550. Min Range: -7.4550

Max Act: 6.9608. Min Act: -0.1700

Data Index: 7956589 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 7.4550. Min Range: -7.4550

Max Act: 6.9629. Min Act: -0.1700

Data Index: 3616142 (Open Web Text)

Max Activating Token Index: 369

Text #19

Max Range: 7.4550. Min Range: -7.4550

Max Act: 6.9149. Min Act: -0.1700

Data Index: 436132 (Open Web Text)

Max Activating Token Index: 1002