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

Dataset: Open Web Text

Neuron 109 in Layer 0

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: 3.1116. Min Range: -3.1116

Max Act: 3.1116. Min Act: -0.1700

Data Index: 1729354 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.9449. Min Act: -0.1700

Data Index: 588784 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.9442. Min Act: -0.1700

Data Index: 6031760 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8830. Min Act: -0.1700

Data Index: 2406079 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8639. Min Act: -0.1700

Data Index: 7560344 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8712. Min Act: -0.1700

Data Index: 7125797 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8523. Min Act: -0.1700

Data Index: 7237205 (Open Web Text)

Max Activating Token Index: 64

Text #7

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8556. Min Act: -0.1700

Data Index: 8411426 (Open Web Text)

Max Activating Token Index: 53

Text #8

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8416. Min Act: -0.1700

Data Index: 5256755 (Open Web Text)

Max Activating Token Index: 858

Text #9

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8427. Min Act: -0.1700

Data Index: 5317728 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8401. Min Act: -0.1700

Data Index: 4715740 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8398. Min Act: -0.1700

Data Index: 4548104 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8314. Min Act: -0.1700

Data Index: 7188421 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8273. Min Act: -0.1700

Data Index: 7026177 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8334. Min Act: -0.1700

Data Index: 6666519 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8333. Min Act: -0.1700

Data Index: 6558605 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8411. Min Act: -0.1700

Data Index: 2101940 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8237. Min Act: -0.1700

Data Index: 981608 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8189. Min Act: -0.1700

Data Index: 1257514 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 3.1116. Min Range: -3.1116

Max Act: 2.8322. Min Act: -0.1700

Data Index: 6486528 (Open Web Text)

Max Activating Token Index: 10