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

Dataset: Open Web Text

Neuron 2739 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: 3.9946. Min Range: -3.9946

Max Act: 3.9946. Min Act: -0.1700

Data Index: 4952304 (Open Web Text)

Max Activating Token Index: 799

Text #1

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9452. Min Act: -0.1700

Data Index: 7475179 (Open Web Text)

Max Activating Token Index: 922

Text #2

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9712. Min Act: -0.1700

Data Index: 8392862 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.9195. Min Act: -0.1700

Data Index: 7294915 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8786. Min Act: -0.1700

Data Index: 1377775 (Open Web Text)

Max Activating Token Index: 773

Text #5

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8728. Min Act: -0.1700

Data Index: 1198998 (Open Web Text)

Max Activating Token Index: 724

Text #6

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.8209. Min Act: -0.1700

Data Index: 4586796 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7877. Min Act: -0.1700

Data Index: 8300025 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7565. Min Act: -0.1700

Data Index: 4943550 (Open Web Text)

Max Activating Token Index: 267

Text #9

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7566. Min Act: -0.1700

Data Index: 2048117 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7154. Min Act: -0.1700

Data Index: 760325 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7369. Min Act: -0.1700

Data Index: 8626836 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7527. Min Act: -0.1700

Data Index: 3343853 (Open Web Text)

Max Activating Token Index: 378

Text #13

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7308. Min Act: -0.1700

Data Index: 6161253 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7237. Min Act: -0.1700

Data Index: 6720146 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7491. Min Act: -0.1700

Data Index: 1964982 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7148. Min Act: -0.1700

Data Index: 1374914 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7199. Min Act: -0.1700

Data Index: 3529454 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7181. Min Act: -0.1700

Data Index: 6181369 (Open Web Text)

Max Activating Token Index: 157

Text #19

Max Range: 3.9946. Min Range: -3.9946

Max Act: 3.7154. Min Act: -0.1700

Data Index: 3584738 (Open Web Text)

Max Activating Token Index: 338