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

Dataset: Open Web Text

Neuron 305 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: 3.3247. Min Range: -3.3247

Max Act: 3.3247. Min Act: -0.1700

Data Index: 1721771 (Open Web Text)

Max Activating Token Index: 411

Text #1

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.2982. Min Act: -0.1700

Data Index: 6538033 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0942. Min Act: -0.1700

Data Index: 496590 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0817. Min Act: -0.1700

Data Index: 2048639 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0790. Min Act: -0.1700

Data Index: 3236179 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1721780 (Open Web Text)

Max Activating Token Index: 662

Text #6

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0304. Min Act: -0.1700

Data Index: 3019986 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0300. Min Act: -0.1700

Data Index: 5798335 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 3.3247. Min Range: -3.3247

Max Act: 3.0084. Min Act: -0.1700

Data Index: 3484537 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9674. Min Act: -0.1700

Data Index: 5769721 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9309. Min Act: -0.1700

Data Index: 5769718 (Open Web Text)

Max Activating Token Index: 708

Text #11

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9470. Min Act: -0.1700

Data Index: 7565244 (Open Web Text)

Max Activating Token Index: 726

Text #12

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9564. Min Act: -0.1700

Data Index: 428282 (Open Web Text)

Max Activating Token Index: 711

Text #13

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.9204. Min Act: -0.1700

Data Index: 3236174 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8710. Min Act: -0.1700

Data Index: 5769715 (Open Web Text)

Max Activating Token Index: 714

Text #15

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8917. Min Act: -0.1700

Data Index: 5669243 (Open Web Text)

Max Activating Token Index: 858

Text #16

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8370. Min Act: -0.1700

Data Index: 1721777 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8553. Min Act: -0.1700

Data Index: 2236092 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8406. Min Act: -0.1700

Data Index: 2406893 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 3.3247. Min Range: -3.3247

Max Act: 2.8305. Min Act: -0.1700

Data Index: 3236173 (Open Web Text)

Max Activating Token Index: 710