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

Dataset: Open Web Text

Neuron 2281 in Layer 4

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: 2.7181. Min Range: -2.7181

Max Act: 2.7181. Min Act: -0.1700

Data Index: 1264234 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6724. Min Act: -0.1700

Data Index: 8748364 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6412. Min Act: -0.1700

Data Index: 3106495 (Open Web Text)

Max Activating Token Index: 221

Text #3

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6560. Min Act: -0.1700

Data Index: 7037074 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6364. Min Act: -0.1700

Data Index: 5106955 (Open Web Text)

Max Activating Token Index: 143

Text #5

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6234. Min Act: -0.1700

Data Index: 7672445 (Open Web Text)

Max Activating Token Index: 971

Text #6

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6377. Min Act: -0.1700

Data Index: 656594 (Open Web Text)

Max Activating Token Index: 447

Text #7

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6225. Min Act: -0.1700

Data Index: 8403158 (Open Web Text)

Max Activating Token Index: 399

Text #8

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6108. Min Act: -0.1700

Data Index: 4246302 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.6008. Min Act: -0.1700

Data Index: 5757942 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5771. Min Act: -0.1700

Data Index: 6726525 (Open Web Text)

Max Activating Token Index: 375

Text #11

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5620. Min Act: -0.1700

Data Index: 7228226 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5635. Min Act: -0.1700

Data Index: 3721201 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5704. Min Act: -0.1700

Data Index: 3735258 (Open Web Text)

Max Activating Token Index: 387

Text #14

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5553. Min Act: -0.1700

Data Index: 1086187 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5504. Min Act: -0.1700

Data Index: 2908573 (Open Web Text)

Max Activating Token Index: 896

Text #16

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5176. Min Act: -0.1700

Data Index: 1722405 (Open Web Text)

Max Activating Token Index: 882

Text #17

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.4915. Min Act: -0.1700

Data Index: 949107 (Open Web Text)

Max Activating Token Index: 937

Text #18

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.5018. Min Act: -0.1700

Data Index: 4219731 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 2.7181. Min Range: -2.7181

Max Act: 2.4895. Min Act: -0.1700

Data Index: 5321787 (Open Web Text)

Max Activating Token Index: 523