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

Dataset: Open Web Text

Neuron 1992 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: 4.7426. Min Range: -4.7426

Max Act: 4.7426. Min Act: -0.1700

Data Index: 5355069 (Open Web Text)

Max Activating Token Index: 522

Text #1

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.7363. Min Act: -0.1700

Data Index: 5262107 (Open Web Text)

Max Activating Token Index: 337

Text #2

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.7058. Min Act: -0.1700

Data Index: 2798011 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.7208. Min Act: -0.1700

Data Index: 39111 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.7160. Min Act: -0.1700

Data Index: 8712069 (Open Web Text)

Max Activating Token Index: 916

Text #5

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6874. Min Act: -0.1700

Data Index: 7570823 (Open Web Text)

Max Activating Token Index: 437

Text #6

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6682. Min Act: -0.1700

Data Index: 1200574 (Open Web Text)

Max Activating Token Index: 340

Text #7

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6803. Min Act: -0.1700

Data Index: 6899666 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6882. Min Act: -0.1700

Data Index: 680880 (Open Web Text)

Max Activating Token Index: 320

Text #9

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6930. Min Act: -0.1700

Data Index: 2918196 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6890. Min Act: -0.1700

Data Index: 8628236 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6804. Min Act: -0.1700

Data Index: 8622930 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6912. Min Act: -0.1700

Data Index: 8261644 (Open Web Text)

Max Activating Token Index: 735

Text #13

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6957. Min Act: -0.1700

Data Index: 6998508 (Open Web Text)

Max Activating Token Index: 440

Text #14

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6589. Min Act: -0.1700

Data Index: 3213487 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6746. Min Act: -0.1700

Data Index: 5070343 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6533. Min Act: -0.1700

Data Index: 1835402 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6709. Min Act: -0.1700

Data Index: 2284025 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6225. Min Act: -0.1700

Data Index: 1166844 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 4.7426. Min Range: -4.7426

Max Act: 4.6207. Min Act: -0.1700

Data Index: 1913098 (Open Web Text)

Max Activating Token Index: 641