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

Dataset: Open Web Text

Neuron 1395 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: 3.5225. Min Range: -3.5225

Max Act: 3.5225. Min Act: -0.1700

Data Index: 6259695 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.4976. Min Act: -0.1700

Data Index: 215663 (Open Web Text)

Max Activating Token Index: 302

Text #2

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3873. Min Act: -0.1700

Data Index: 6379222 (Open Web Text)

Max Activating Token Index: 445

Text #3

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3949. Min Act: -0.1700

Data Index: 743399 (Open Web Text)

Max Activating Token Index: 306

Text #4

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3718. Min Act: -0.1700

Data Index: 3438567 (Open Web Text)

Max Activating Token Index: 174

Text #5

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3745. Min Act: -0.1700

Data Index: 1939702 (Open Web Text)

Max Activating Token Index: 665

Text #6

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3237. Min Act: -0.1700

Data Index: 5901647 (Open Web Text)

Max Activating Token Index: 841

Text #7

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3410. Min Act: -0.1700

Data Index: 6820353 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3279. Min Act: -0.1700

Data Index: 966 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3315. Min Act: -0.1700

Data Index: 2384862 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3064. Min Act: -0.1700

Data Index: 6335105 (Open Web Text)

Max Activating Token Index: 952

Text #11

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3094. Min Act: -0.1700

Data Index: 4313332 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.2898. Min Act: -0.1700

Data Index: 3202379 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.3043. Min Act: -0.1700

Data Index: 3324858 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.2754. Min Act: -0.1700

Data Index: 6192620 (Open Web Text)

Max Activating Token Index: 910

Text #15

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.2560. Min Act: -0.1700

Data Index: 5292450 (Open Web Text)

Max Activating Token Index: 139

Text #16

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.2562. Min Act: -0.1700

Data Index: 1672444 (Open Web Text)

Max Activating Token Index: 195

Text #17

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.2493. Min Act: -0.1700

Data Index: 5605762 (Open Web Text)

Max Activating Token Index: 613

Text #18

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.2281. Min Act: -0.1700

Data Index: 4274576 (Open Web Text)

Max Activating Token Index: 497

Text #19

Max Range: 3.5225. Min Range: -3.5225

Max Act: 3.2158. Min Act: -0.1700

Data Index: 771128 (Open Web Text)

Max Activating Token Index: 347