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

Dataset: Open Web Text

Neuron 147 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: 4.7090. Min Range: -4.7090

Max Act: 4.7090. Min Act: -0.1700

Data Index: 5169548 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.6425. Min Act: -0.1700

Data Index: 539376 (Open Web Text)

Max Activating Token Index: 236

Text #2

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5364. Min Act: -0.1700

Data Index: 913217 (Open Web Text)

Max Activating Token Index: 722

Text #3

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.6817. Min Act: -0.1700

Data Index: 2677505 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5776. Min Act: -0.1700

Data Index: 3034425 (Open Web Text)

Max Activating Token Index: 526

Text #5

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.6119. Min Act: -0.1700

Data Index: 2741955 (Open Web Text)

Max Activating Token Index: 335

Text #6

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5912. Min Act: -0.1700

Data Index: 4841066 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5732. Min Act: -0.1700

Data Index: 1509892 (Open Web Text)

Max Activating Token Index: 216

Text #8

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5211. Min Act: -0.1700

Data Index: 2677503 (Open Web Text)

Max Activating Token Index: 561

Text #9

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5489. Min Act: -0.1700

Data Index: 2486118 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5690. Min Act: -0.1700

Data Index: 4676559 (Open Web Text)

Max Activating Token Index: 782

Text #11

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5580. Min Act: -0.1700

Data Index: 7926966 (Open Web Text)

Max Activating Token Index: 812

Text #12

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5539. Min Act: -0.1700

Data Index: 4596419 (Open Web Text)

Max Activating Token Index: 462

Text #13

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5912. Min Act: -0.1700

Data Index: 3846805 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5136. Min Act: -0.1700

Data Index: 3690421 (Open Web Text)

Max Activating Token Index: 526

Text #15

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5514. Min Act: -0.1700

Data Index: 2010937 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.4966. Min Act: -0.1700

Data Index: 4222697 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5442. Min Act: -0.1700

Data Index: 4280293 (Open Web Text)

Max Activating Token Index: 306

Text #18

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5552. Min Act: -0.1700

Data Index: 4376506 (Open Web Text)

Max Activating Token Index: 676

Text #19

Max Range: 4.7090. Min Range: -4.7090

Max Act: 4.5347. Min Act: -0.1700

Data Index: 2942956 (Open Web Text)

Max Activating Token Index: 670