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

Dataset: Open Web Text

Neuron 967 in Layer 1

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: 4.9002. Min Range: -4.9002

Max Act: 4.9002. Min Act: -0.1700

Data Index: 4822623 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.8676. Min Act: -0.1700

Data Index: 4032238 (Open Web Text)

Max Activating Token Index: 339

Text #2

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.8312. Min Act: -0.1700

Data Index: 448950 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.8119. Min Act: -0.1700

Data Index: 2538454 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.8017. Min Act: -0.1700

Data Index: 3811820 (Open Web Text)

Max Activating Token Index: 674

Text #5

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7662. Min Act: -0.1700

Data Index: 1386117 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7551. Min Act: -0.1700

Data Index: 2248819 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7782. Min Act: -0.1700

Data Index: 3615170 (Open Web Text)

Max Activating Token Index: 270

Text #8

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7677. Min Act: -0.1700

Data Index: 3592423 (Open Web Text)

Max Activating Token Index: 866

Text #9

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7821. Min Act: -0.1700

Data Index: 3545109 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7835. Min Act: -0.1700

Data Index: 5019150 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7516. Min Act: -0.1700

Data Index: 1583876 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7468. Min Act: -0.1700

Data Index: 3319434 (Open Web Text)

Max Activating Token Index: 646

Text #13

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7481. Min Act: -0.1700

Data Index: 3159663 (Open Web Text)

Max Activating Token Index: 638

Text #14

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7170. Min Act: -0.1700

Data Index: 1669470 (Open Web Text)

Max Activating Token Index: 449

Text #15

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7428. Min Act: -0.1700

Data Index: 1584371 (Open Web Text)

Max Activating Token Index: 211

Text #16

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7174. Min Act: -0.1700

Data Index: 2899044 (Open Web Text)

Max Activating Token Index: 222

Text #17

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7217. Min Act: -0.1700

Data Index: 3776108 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7035. Min Act: -0.1700

Data Index: 2308716 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 4.9002. Min Range: -4.9002

Max Act: 4.7351. Min Act: -0.1700

Data Index: 3777231 (Open Web Text)

Max Activating Token Index: 648