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

Dataset: Open Web Text

Neuron 1929 in Layer 5

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: 3.1155. Min Range: -3.1155

Max Act: 3.1155. Min Act: -0.1700

Data Index: 7843210 (Open Web Text)

Max Activating Token Index: 711

Text #1

Max Range: 3.1155. Min Range: -3.1155

Max Act: 3.0864. Min Act: -0.1700

Data Index: 6527755 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 3.1155. Min Range: -3.1155

Max Act: 3.0393. Min Act: -0.1700

Data Index: 5736668 (Open Web Text)

Max Activating Token Index: 106

Text #3

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9786. Min Act: -0.1700

Data Index: 7791798 (Open Web Text)

Max Activating Token Index: 798

Text #4

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9461. Min Act: -0.1700

Data Index: 1764837 (Open Web Text)

Max Activating Token Index: 798

Text #5

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9515. Min Act: -0.1700

Data Index: 3228186 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9531. Min Act: -0.1700

Data Index: 6363561 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9602. Min Act: -0.1700

Data Index: 2187940 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9644. Min Act: -0.1700

Data Index: 7122653 (Open Web Text)

Max Activating Token Index: 742

Text #9

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9371. Min Act: -0.1700

Data Index: 4548967 (Open Web Text)

Max Activating Token Index: 597

Text #10

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9604. Min Act: -0.1700

Data Index: 5535967 (Open Web Text)

Max Activating Token Index: 973

Text #11

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.8925. Min Act: -0.1700

Data Index: 1876877 (Open Web Text)

Max Activating Token Index: 985

Text #12

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9038. Min Act: -0.1700

Data Index: 1804024 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.8751. Min Act: -0.1700

Data Index: 8149563 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9032. Min Act: -0.1700

Data Index: 1369525 (Open Web Text)

Max Activating Token Index: 316

Text #15

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.8962. Min Act: -0.1700

Data Index: 2808586 (Open Web Text)

Max Activating Token Index: 359

Text #16

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.8954. Min Act: -0.1700

Data Index: 1864398 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.8910. Min Act: -0.1700

Data Index: 1905548 (Open Web Text)

Max Activating Token Index: 248

Text #18

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.9039. Min Act: -0.1700

Data Index: 5719530 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 3.1155. Min Range: -3.1155

Max Act: 2.8697. Min Act: -0.1700

Data Index: 4674588 (Open Web Text)

Max Activating Token Index: 454