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

Dataset: Open Web Text

Neuron 1803 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: 4.4491. Min Range: -4.4491

Max Act: 4.4491. Min Act: -0.1700

Data Index: 4635829 (Open Web Text)

Max Activating Token Index: 179

Text #1

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.4019. Min Act: -0.1700

Data Index: 1251614 (Open Web Text)

Max Activating Token Index: 239

Text #2

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3807. Min Act: -0.1700

Data Index: 8142376 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3692. Min Act: -0.1700

Data Index: 3064733 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3563. Min Act: -0.1700

Data Index: 468256 (Open Web Text)

Max Activating Token Index: 248

Text #5

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3953. Min Act: -0.1700

Data Index: 1363186 (Open Web Text)

Max Activating Token Index: 492

Text #6

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3732. Min Act: -0.1700

Data Index: 4611154 (Open Web Text)

Max Activating Token Index: 217

Text #7

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3454. Min Act: -0.1700

Data Index: 7424126 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3457. Min Act: -0.1700

Data Index: 7207163 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3656. Min Act: -0.1700

Data Index: 3298294 (Open Web Text)

Max Activating Token Index: 311

Text #10

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3641. Min Act: -0.1700

Data Index: 2668 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3361. Min Act: -0.1700

Data Index: 8333339 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3603. Min Act: -0.1700

Data Index: 7261682 (Open Web Text)

Max Activating Token Index: 451

Text #13

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3180. Min Act: -0.1700

Data Index: 4258650 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3038. Min Act: -0.1700

Data Index: 708228 (Open Web Text)

Max Activating Token Index: 74

Text #15

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3227. Min Act: -0.1700

Data Index: 4237937 (Open Web Text)

Max Activating Token Index: 76

Text #16

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3266. Min Act: -0.1700

Data Index: 6129534 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3372. Min Act: -0.1700

Data Index: 6752998 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3124. Min Act: -0.1700

Data Index: 2353366 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 4.4491. Min Range: -4.4491

Max Act: 4.3383. Min Act: -0.1700

Data Index: 1861366 (Open Web Text)

Max Activating Token Index: 64