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

Dataset: Open Web Text

Neuron 1157 in Layer 3

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: 3.6907. Min Range: -3.6907

Max Act: 3.6907. Min Act: -0.1700

Data Index: 4007310 (Open Web Text)

Max Activating Token Index: 866

Text #1

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.6585. Min Act: -0.1700

Data Index: 5344937 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.6457. Min Act: -0.1700

Data Index: 8093502 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5967. Min Act: -0.1700

Data Index: 8189273 (Open Web Text)

Max Activating Token Index: 375

Text #4

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5619. Min Act: -0.1700

Data Index: 2738211 (Open Web Text)

Max Activating Token Index: 156

Text #5

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5634. Min Act: -0.1700

Data Index: 486124 (Open Web Text)

Max Activating Token Index: 835

Text #6

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5444. Min Act: -0.1700

Data Index: 4246394 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5316. Min Act: -0.1700

Data Index: 1958155 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5407. Min Act: -0.1700

Data Index: 1902570 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5043. Min Act: -0.1700

Data Index: 607160 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.5166. Min Act: -0.1700

Data Index: 203689 (Open Web Text)

Max Activating Token Index: 663

Text #11

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4954. Min Act: -0.1700

Data Index: 486128 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4507. Min Act: -0.1700

Data Index: 2454551 (Open Web Text)

Max Activating Token Index: 626

Text #13

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4936. Min Act: -0.1700

Data Index: 1287941 (Open Web Text)

Max Activating Token Index: 596

Text #14

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4332. Min Act: -0.1700

Data Index: 5614423 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4550. Min Act: -0.1700

Data Index: 5347828 (Open Web Text)

Max Activating Token Index: 458

Text #16

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4211. Min Act: -0.1700

Data Index: 2838775 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4505. Min Act: -0.1700

Data Index: 7180297 (Open Web Text)

Max Activating Token Index: 599

Text #18

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4271. Min Act: -0.1700

Data Index: 1570967 (Open Web Text)

Max Activating Token Index: 794

Text #19

Max Range: 3.6907. Min Range: -3.6907

Max Act: 3.4249. Min Act: -0.1700

Data Index: 1498691 (Open Web Text)

Max Activating Token Index: 1020