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

Dataset: Open Web Text

Neuron 234 in Layer 5

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: 4.1330. Min Range: -4.1330

Max Act: 4.1330. Min Act: -0.1700

Data Index: 7806971 (Open Web Text)

Max Activating Token Index: 870

Text #1

Max Range: 4.1330. Min Range: -4.1330

Max Act: 4.0555. Min Act: -0.1700

Data Index: 8211203 (Open Web Text)

Max Activating Token Index: 943

Text #2

Max Range: 4.1330. Min Range: -4.1330

Max Act: 4.0131. Min Act: -0.1700

Data Index: 203052 (Open Web Text)

Max Activating Token Index: 90

Text #3

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.9152. Min Act: -0.1700

Data Index: 1965443 (Open Web Text)

Max Activating Token Index: 954

Text #4

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.9438. Min Act: -0.1700

Data Index: 2927403 (Open Web Text)

Max Activating Token Index: 791

Text #5

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.9039. Min Act: -0.1700

Data Index: 894307 (Open Web Text)

Max Activating Token Index: 465

Text #6

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8965. Min Act: -0.1700

Data Index: 6115177 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8709. Min Act: -0.1700

Data Index: 5596377 (Open Web Text)

Max Activating Token Index: 605

Text #8

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8453. Min Act: -0.1700

Data Index: 4618249 (Open Web Text)

Max Activating Token Index: 757

Text #9

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8719. Min Act: -0.1700

Data Index: 4802297 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8413. Min Act: -0.1700

Data Index: 8252822 (Open Web Text)

Max Activating Token Index: 249

Text #11

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8633. Min Act: -0.1700

Data Index: 7711800 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8494. Min Act: -0.1700

Data Index: 3234466 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8093. Min Act: -0.1700

Data Index: 6661308 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8188. Min Act: -0.1700

Data Index: 6517790 (Open Web Text)

Max Activating Token Index: 328

Text #15

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8177. Min Act: -0.1700

Data Index: 6742597 (Open Web Text)

Max Activating Token Index: 159

Text #16

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8177. Min Act: -0.1700

Data Index: 3394330 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8028. Min Act: -0.1700

Data Index: 7912749 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.8145. Min Act: -0.1700

Data Index: 6396427 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 4.1330. Min Range: -4.1330

Max Act: 3.7807. Min Act: -0.1700

Data Index: 6100015 (Open Web Text)

Max Activating Token Index: 119