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

Dataset: Open Web Text

Neuron 2226 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: 5.0438. Min Range: -5.0438

Max Act: 5.0438. Min Act: -0.1700

Data Index: 2799313 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.9293. Min Act: -0.1700

Data Index: 4855865 (Open Web Text)

Max Activating Token Index: 625

Text #2

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.9387. Min Act: -0.1700

Data Index: 2229531 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.9551. Min Act: -0.1700

Data Index: 7843836 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.9245. Min Act: -0.1700

Data Index: 6659518 (Open Web Text)

Max Activating Token Index: 724

Text #5

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.9301. Min Act: -0.1700

Data Index: 2404021 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8692. Min Act: -0.1700

Data Index: 7251696 (Open Web Text)

Max Activating Token Index: 657

Text #7

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8627. Min Act: -0.1700

Data Index: 7401651 (Open Web Text)

Max Activating Token Index: 690

Text #8

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8333. Min Act: -0.1700

Data Index: 139519 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.7935. Min Act: -0.1700

Data Index: 5364753 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8316. Min Act: -0.1700

Data Index: 1909533 (Open Web Text)

Max Activating Token Index: 575

Text #11

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8362. Min Act: -0.1700

Data Index: 5209791 (Open Web Text)

Max Activating Token Index: 412

Text #12

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8369. Min Act: -0.1700

Data Index: 714620 (Open Web Text)

Max Activating Token Index: 560

Text #13

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8257. Min Act: -0.1700

Data Index: 6978401 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8303. Min Act: -0.1700

Data Index: 6372244 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.7943. Min Act: -0.1700

Data Index: 5742583 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.8090. Min Act: -0.1700

Data Index: 7366027 (Open Web Text)

Max Activating Token Index: 832

Text #17

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.7789. Min Act: -0.1700

Data Index: 1381464 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.7779. Min Act: -0.1700

Data Index: 3725476 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 5.0438. Min Range: -5.0438

Max Act: 4.7964. Min Act: -0.1700

Data Index: 4505412 (Open Web Text)

Max Activating Token Index: 682