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

Dataset: Open Web Text

Neuron 2300 in Layer 1

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: 3.1627. Min Range: -3.1627

Max Act: 3.1627. Min Act: -0.1700

Data Index: 3491681 (Open Web Text)

Max Activating Token Index: 942

Text #1

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.1203. Min Act: -0.1700

Data Index: 7493083 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.1088. Min Act: -0.1700

Data Index: 8538484 (Open Web Text)

Max Activating Token Index: 418

Text #3

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0864. Min Act: -0.1700

Data Index: 2061022 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0792. Min Act: -0.1700

Data Index: 1176869 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0586. Min Act: -0.1700

Data Index: 6687586 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0350. Min Act: -0.1700

Data Index: 2256877 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0424. Min Act: -0.1700

Data Index: 7413012 (Open Web Text)

Max Activating Token Index: 588

Text #8

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0569. Min Act: -0.1700

Data Index: 5041294 (Open Web Text)

Max Activating Token Index: 966

Text #9

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0475. Min Act: -0.1700

Data Index: 3074250 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0562. Min Act: -0.1700

Data Index: 926451 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0397. Min Act: -0.1700

Data Index: 148677 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0333. Min Act: -0.1700

Data Index: 8403415 (Open Web Text)

Max Activating Token Index: 752

Text #13

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0216. Min Act: -0.1700

Data Index: 1213978 (Open Web Text)

Max Activating Token Index: 969

Text #14

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0535. Min Act: -0.1700

Data Index: 6032971 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0275. Min Act: -0.1700

Data Index: 4455662 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0382. Min Act: -0.1700

Data Index: 4663380 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0201. Min Act: -0.1700

Data Index: 5901021 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0098. Min Act: -0.1700

Data Index: 2792419 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 3.1627. Min Range: -3.1627

Max Act: 3.0023. Min Act: -0.1700

Data Index: 2348108 (Open Web Text)

Max Activating Token Index: 93