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

Dataset: Open Web Text

Neuron 2133 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: 6.8735. Min Range: -6.8735

Max Act: 6.8735. Min Act: -0.1700

Data Index: 1232539 (Open Web Text)

Max Activating Token Index: 215

Text #1

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.8487. Min Act: -0.1700

Data Index: 4989632 (Open Web Text)

Max Activating Token Index: 698

Text #2

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.8408. Min Act: -0.1700

Data Index: 806454 (Open Web Text)

Max Activating Token Index: 216

Text #3

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.8145. Min Act: -0.1700

Data Index: 7796919 (Open Web Text)

Max Activating Token Index: 132

Text #4

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.7384. Min Act: -0.1700

Data Index: 6727510 (Open Web Text)

Max Activating Token Index: 839

Text #5

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.6444. Min Act: -0.1700

Data Index: 101932 (Open Web Text)

Max Activating Token Index: 163

Text #6

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.6223. Min Act: -0.1700

Data Index: 1558326 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5292. Min Act: -0.1700

Data Index: 223262 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5982. Min Act: -0.1700

Data Index: 6356467 (Open Web Text)

Max Activating Token Index: 597

Text #9

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.6658. Min Act: -0.1700

Data Index: 2115075 (Open Web Text)

Max Activating Token Index: 280

Text #10

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5821. Min Act: -0.1700

Data Index: 1530900 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.6450. Min Act: -0.1700

Data Index: 2397359 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5744. Min Act: -0.1700

Data Index: 1306932 (Open Web Text)

Max Activating Token Index: 241

Text #13

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.4608. Min Act: -0.1700

Data Index: 5379339 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5021. Min Act: -0.1700

Data Index: 5912959 (Open Web Text)

Max Activating Token Index: 189

Text #15

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5303. Min Act: -0.1700

Data Index: 3695196 (Open Web Text)

Max Activating Token Index: 247

Text #16

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.4718. Min Act: -0.1700

Data Index: 1159081 (Open Web Text)

Max Activating Token Index: 1003

Text #17

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5413. Min Act: -0.1700

Data Index: 1976247 (Open Web Text)

Max Activating Token Index: 825

Text #18

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5433. Min Act: -0.1700

Data Index: 3911602 (Open Web Text)

Max Activating Token Index: 275

Text #19

Max Range: 6.8735. Min Range: -6.8735

Max Act: 6.5116. Min Act: -0.1700

Data Index: 4133482 (Open Web Text)

Max Activating Token Index: 791