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

Dataset: Open Web Text

Neuron 1791 in Layer 2

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: 1.4206. Min Range: -1.4206

Max Act: 1.4206. Min Act: -0.1700

Data Index: 714216 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3833. Min Act: -0.1700

Data Index: 4748963 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3780. Min Act: -0.1699

Data Index: 4840667 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3769. Min Act: -0.1688

Data Index: 3398714 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3703. Min Act: -0.1700

Data Index: 6881730 (Open Web Text)

Max Activating Token Index: 394

Text #5

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3671. Min Act: -0.1700

Data Index: 295983 (Open Web Text)

Max Activating Token Index: 303

Text #6

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3513. Min Act: -0.1700

Data Index: 2983976 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3454. Min Act: -0.1153

Data Index: 6393179 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3734. Min Act: -0.1700

Data Index: 4753280 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3588. Min Act: -0.1700

Data Index: 1272980 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3584. Min Act: -0.1700

Data Index: 1074493 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3502. Min Act: -0.1689

Data Index: 7692704 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3539. Min Act: -0.1513

Data Index: 2725417 (Open Web Text)

Max Activating Token Index: 301

Text #13

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3466. Min Act: -0.1700

Data Index: 1834326 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3518. Min Act: -0.1696

Data Index: 4535081 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3528. Min Act: -0.1695

Data Index: 859189 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3390. Min Act: -0.1700

Data Index: 6381371 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3389. Min Act: -0.1700

Data Index: 350570 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3403. Min Act: -0.1700

Data Index: 24309 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.4206. Min Range: -1.4206

Max Act: 1.3474. Min Act: -0.1608

Data Index: 6393177 (Open Web Text)

Max Activating Token Index: 397