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

Dataset: Open Web Text

Neuron 1766 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: 3.3191. Min Range: -3.3191

Max Act: 3.3191. Min Act: -0.1700

Data Index: 2761780 (Open Web Text)

Max Activating Token Index: 659

Text #1

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.2763. Min Act: -0.1700

Data Index: 4403760 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.2204. Min Act: -0.1700

Data Index: 1779418 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.2018. Min Act: -0.1700

Data Index: 52081 (Open Web Text)

Max Activating Token Index: 700

Text #4

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.2039. Min Act: -0.1700

Data Index: 3316506 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1862. Min Act: -0.1700

Data Index: 3436433 (Open Web Text)

Max Activating Token Index: 699

Text #6

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1749. Min Act: -0.1700

Data Index: 768614 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1785. Min Act: -0.1700

Data Index: 6113553 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1657. Min Act: -0.1700

Data Index: 3711961 (Open Web Text)

Max Activating Token Index: 144

Text #9

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1711. Min Act: -0.1700

Data Index: 6923144 (Open Web Text)

Max Activating Token Index: 728

Text #10

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1647. Min Act: -0.1700

Data Index: 954592 (Open Web Text)

Max Activating Token Index: 430

Text #11

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1588. Min Act: -0.1700

Data Index: 8076521 (Open Web Text)

Max Activating Token Index: 566

Text #12

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1538. Min Act: -0.1700

Data Index: 5741711 (Open Web Text)

Max Activating Token Index: 618

Text #13

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1652. Min Act: -0.1700

Data Index: 2499204 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1425. Min Act: -0.1700

Data Index: 3618572 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1405. Min Act: -0.1700

Data Index: 7056905 (Open Web Text)

Max Activating Token Index: 880

Text #16

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1526. Min Act: -0.1700

Data Index: 2298092 (Open Web Text)

Max Activating Token Index: 896

Text #17

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1132. Min Act: -0.1700

Data Index: 2465394 (Open Web Text)

Max Activating Token Index: 634

Text #18

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1331. Min Act: -0.1700

Data Index: 1237699 (Open Web Text)

Max Activating Token Index: 494

Text #19

Max Range: 3.3191. Min Range: -3.3191

Max Act: 3.1435. Min Act: -0.1700

Data Index: 456889 (Open Web Text)

Max Activating Token Index: 400