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

Dataset: Open Web Text

Neuron 399 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: 3.3752. Min Range: -3.3752

Max Act: 3.3752. Min Act: -0.1700

Data Index: 565251 (Open Web Text)

Max Activating Token Index: 610

Text #1

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.3421. Min Act: -0.1700

Data Index: 5269945 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.3449. Min Act: -0.1700

Data Index: 1012178 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2907. Min Act: -0.1700

Data Index: 73154 (Open Web Text)

Max Activating Token Index: 360

Text #4

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2866. Min Act: -0.1700

Data Index: 7254796 (Open Web Text)

Max Activating Token Index: 400

Text #5

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2783. Min Act: -0.1700

Data Index: 4342617 (Open Web Text)

Max Activating Token Index: 286

Text #6

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2905. Min Act: -0.1700

Data Index: 6049663 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2826. Min Act: -0.1700

Data Index: 6057622 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2728. Min Act: -0.1700

Data Index: 1231994 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2728. Min Act: -0.1700

Data Index: 6984126 (Open Web Text)

Max Activating Token Index: 680

Text #10

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2429. Min Act: -0.1700

Data Index: 2331850 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2577. Min Act: -0.1700

Data Index: 5007077 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2620. Min Act: -0.1700

Data Index: 2348742 (Open Web Text)

Max Activating Token Index: 726

Text #13

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2413. Min Act: -0.1700

Data Index: 1408536 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2300. Min Act: -0.1700

Data Index: 1488712 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2369. Min Act: -0.1700

Data Index: 7465318 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2301. Min Act: -0.1700

Data Index: 561410 (Open Web Text)

Max Activating Token Index: 95

Text #17

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2542. Min Act: -0.1700

Data Index: 2158009 (Open Web Text)

Max Activating Token Index: 907

Text #18

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2210. Min Act: -0.1700

Data Index: 293472 (Open Web Text)

Max Activating Token Index: 590

Text #19

Max Range: 3.3752. Min Range: -3.3752

Max Act: 3.2310. Min Act: -0.1700

Data Index: 800744 (Open Web Text)

Max Activating Token Index: 536