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

Dataset: Open Web Text

Neuron 2386 in Layer 5

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: 4.7582. Min Range: -4.7582

Max Act: 4.7582. Min Act: -0.1700

Data Index: 2692374 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.5391. Min Act: -0.1700

Data Index: 5600604 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.5105. Min Act: -0.1700

Data Index: 2906967 (Open Web Text)

Max Activating Token Index: 657

Text #3

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.4730. Min Act: -0.1700

Data Index: 5453079 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.4878. Min Act: -0.1700

Data Index: 1286835 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.4479. Min Act: -0.1700

Data Index: 2536588 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3878. Min Act: -0.1700

Data Index: 4293570 (Open Web Text)

Max Activating Token Index: 806

Text #7

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.4329. Min Act: -0.1700

Data Index: 7120686 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3545. Min Act: -0.1700

Data Index: 6158488 (Open Web Text)

Max Activating Token Index: 380

Text #9

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3162. Min Act: -0.1700

Data Index: 808992 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3392. Min Act: -0.1700

Data Index: 1587251 (Open Web Text)

Max Activating Token Index: 898

Text #11

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3398. Min Act: -0.1700

Data Index: 6194413 (Open Web Text)

Max Activating Token Index: 1004

Text #12

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3507. Min Act: -0.1700

Data Index: 4914300 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3054. Min Act: -0.1700

Data Index: 5543905 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3047. Min Act: -0.1700

Data Index: 5985022 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3110. Min Act: -0.1700

Data Index: 4663875 (Open Web Text)

Max Activating Token Index: 657

Text #16

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3188. Min Act: -0.1700

Data Index: 2295644 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3334. Min Act: -0.1700

Data Index: 3775340 (Open Web Text)

Max Activating Token Index: 610

Text #18

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.3375. Min Act: -0.1700

Data Index: 1565697 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 4.7582. Min Range: -4.7582

Max Act: 4.2809. Min Act: -0.1700

Data Index: 3982632 (Open Web Text)

Max Activating Token Index: 7