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

Dataset: Open Web Text

Neuron 2605 in Layer 4

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: 5.4406. Min Range: -5.4406

Max Act: 5.4406. Min Act: -0.1700

Data Index: 3064969 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.3149. Min Act: -0.1700

Data Index: 7723183 (Open Web Text)

Max Activating Token Index: 734

Text #2

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.3008. Min Act: -0.1700

Data Index: 3330434 (Open Web Text)

Max Activating Token Index: 368

Text #3

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.2517. Min Act: -0.1700

Data Index: 4723284 (Open Web Text)

Max Activating Token Index: 278

Text #4

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1984. Min Act: -0.1700

Data Index: 3448932 (Open Web Text)

Max Activating Token Index: 879

Text #5

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1621. Min Act: -0.1700

Data Index: 3549920 (Open Web Text)

Max Activating Token Index: 262

Text #6

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1320. Min Act: -0.1700

Data Index: 7979458 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1306. Min Act: -0.1700

Data Index: 1175797 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1170. Min Act: -0.1700

Data Index: 3516647 (Open Web Text)

Max Activating Token Index: 684

Text #9

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1032. Min Act: -0.1700

Data Index: 3348197 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0951. Min Act: -0.1700

Data Index: 3905997 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1398. Min Act: -0.1700

Data Index: 5724021 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.1283. Min Act: -0.1700

Data Index: 687316 (Open Web Text)

Max Activating Token Index: 553

Text #13

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0849. Min Act: -0.1700

Data Index: 4158070 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0734. Min Act: -0.1700

Data Index: 2417606 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0581. Min Act: -0.1700

Data Index: 7667733 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0801. Min Act: -0.1700

Data Index: 3470362 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0854. Min Act: -0.1700

Data Index: 3711247 (Open Web Text)

Max Activating Token Index: 829

Text #18

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0508. Min Act: -0.1700

Data Index: 5878614 (Open Web Text)

Max Activating Token Index: 849

Text #19

Max Range: 5.4406. Min Range: -5.4406

Max Act: 5.0549. Min Act: -0.1700

Data Index: 6740421 (Open Web Text)

Max Activating Token Index: 941