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

Dataset: Open Web Text

Neuron 2342 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: 3.7710. Min Range: -3.7710

Max Act: 3.7562. Min Act: -0.1700

Data Index: 3147969 (Open Web Text)

Max Activating Token Index: 591

Text #1

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.7710. Min Act: -0.1700

Data Index: 6026243 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.7269. Min Act: -0.1700

Data Index: 1577582 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6584. Min Act: -0.1700

Data Index: 7250820 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6749. Min Act: -0.1700

Data Index: 4835280 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6982. Min Act: -0.1700

Data Index: 6081189 (Open Web Text)

Max Activating Token Index: 726

Text #6

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.7007. Min Act: -0.1700

Data Index: 4268508 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6834. Min Act: -0.1700

Data Index: 5523835 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6964. Min Act: -0.1700

Data Index: 1795037 (Open Web Text)

Max Activating Token Index: 765

Text #9

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6735. Min Act: -0.1700

Data Index: 5233085 (Open Web Text)

Max Activating Token Index: 478

Text #10

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6501. Min Act: -0.1700

Data Index: 252158 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6425. Min Act: -0.1700

Data Index: 5880027 (Open Web Text)

Max Activating Token Index: 607

Text #12

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6377. Min Act: -0.1700

Data Index: 464719 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6627. Min Act: -0.1700

Data Index: 3781802 (Open Web Text)

Max Activating Token Index: 412

Text #14

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6291. Min Act: -0.1700

Data Index: 1055960 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6647. Min Act: -0.1700

Data Index: 5490884 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6532. Min Act: -0.1700

Data Index: 6624806 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6658. Min Act: -0.1700

Data Index: 4707911 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6328. Min Act: -0.1700

Data Index: 3100682 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.6285. Min Act: -0.1700

Data Index: 290582 (Open Web Text)

Max Activating Token Index: 939