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

Dataset: Open Web Text

Neuron 646 in Layer 6

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: 3.2497. Min Range: -3.2497

Max Act: 3.2497. Min Act: -0.1700

Data Index: 6407014 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.1124. Min Act: -0.1700

Data Index: 1596209 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.1002. Min Act: -0.1700

Data Index: 3507199 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.1172. Min Act: -0.1700

Data Index: 979574 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0906. Min Act: -0.1700

Data Index: 8691187 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.1013. Min Act: -0.1700

Data Index: 7875544 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0836. Min Act: -0.1700

Data Index: 3936632 (Open Web Text)

Max Activating Token Index: 169

Text #7

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0663. Min Act: -0.1700

Data Index: 7540864 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0497. Min Act: -0.1700

Data Index: 5244573 (Open Web Text)

Max Activating Token Index: 367

Text #9

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0721. Min Act: -0.1700

Data Index: 5285022 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0226. Min Act: -0.1700

Data Index: 6721569 (Open Web Text)

Max Activating Token Index: 343

Text #11

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0023. Min Act: -0.1700

Data Index: 8471262 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0019. Min Act: -0.1700

Data Index: 5623985 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0071. Min Act: -0.1700

Data Index: 126382 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0082. Min Act: -0.1700

Data Index: 841793 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0383. Min Act: -0.1700

Data Index: 3186473 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.9856. Min Act: -0.1700

Data Index: 366012 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.9561. Min Act: -0.1700

Data Index: 3238617 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.9608. Min Act: -0.1700

Data Index: 8235573 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.9681. Min Act: -0.1700

Data Index: 4894506 (Open Web Text)

Max Activating Token Index: 883