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

Dataset: Open Web Text

Neuron 2994 in Layer 2

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: 4.2206. Min Range: -4.2206

Max Act: 4.2206. Min Act: -0.1700

Data Index: 6538590 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.2206. Min Range: -4.2206

Max Act: 4.1919. Min Act: -0.1700

Data Index: 4663325 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.2206. Min Range: -4.2206

Max Act: 4.0796. Min Act: -0.1700

Data Index: 8111007 (Open Web Text)

Max Activating Token Index: 671

Text #3

Max Range: 4.2206. Min Range: -4.2206

Max Act: 4.0114. Min Act: -0.1700

Data Index: 8357287 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9490. Min Act: -0.1700

Data Index: 4722970 (Open Web Text)

Max Activating Token Index: 761

Text #5

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9365. Min Act: -0.1700

Data Index: 8364950 (Open Web Text)

Max Activating Token Index: 903

Text #6

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9557. Min Act: -0.1700

Data Index: 7218019 (Open Web Text)

Max Activating Token Index: 359

Text #7

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9529. Min Act: -0.1700

Data Index: 6728035 (Open Web Text)

Max Activating Token Index: 525

Text #8

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9012. Min Act: -0.1700

Data Index: 7899195 (Open Web Text)

Max Activating Token Index: 148

Text #9

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9028. Min Act: -0.1700

Data Index: 5312503 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9217. Min Act: -0.1700

Data Index: 5833271 (Open Web Text)

Max Activating Token Index: 214

Text #11

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9248. Min Act: -0.1700

Data Index: 6274116 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.8975. Min Act: -0.1700

Data Index: 4624474 (Open Web Text)

Max Activating Token Index: 498

Text #13

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9042. Min Act: -0.1700

Data Index: 2030001 (Open Web Text)

Max Activating Token Index: 947

Text #14

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.8905. Min Act: -0.1700

Data Index: 4223802 (Open Web Text)

Max Activating Token Index: 863

Text #15

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.8966. Min Act: -0.1700

Data Index: 7544426 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.8613. Min Act: -0.1700

Data Index: 7063903 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.8700. Min Act: -0.1700

Data Index: 6589538 (Open Web Text)

Max Activating Token Index: 278

Text #18

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.9016. Min Act: -0.1700

Data Index: 1198173 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 4.2206. Min Range: -4.2206

Max Act: 3.8729. Min Act: -0.1700

Data Index: 6468468 (Open Web Text)

Max Activating Token Index: 50