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

Dataset: Open Web Text

Neuron 1593 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: 3.2785. Min Range: -3.2785

Max Act: 3.2785. Min Act: -0.1700

Data Index: 4936887 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.2214. Min Act: -0.1700

Data Index: 1733524 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.2208. Min Act: -0.1700

Data Index: 2799476 (Open Web Text)

Max Activating Token Index: 25

Text #3

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.2009. Min Act: -0.1700

Data Index: 6924976 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.2049. Min Act: -0.1700

Data Index: 3044750 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.2137. Min Act: -0.1700

Data Index: 7471667 (Open Web Text)

Max Activating Token Index: 305

Text #6

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.2097. Min Act: -0.1700

Data Index: 4048338 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1609. Min Act: -0.1700

Data Index: 7178572 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1830. Min Act: -0.1700

Data Index: 4184931 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1846. Min Act: -0.1700

Data Index: 7792629 (Open Web Text)

Max Activating Token Index: 33

Text #10

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1629. Min Act: -0.1700

Data Index: 3308376 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1584. Min Act: -0.1700

Data Index: 7380803 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1730. Min Act: -0.1700

Data Index: 4617467 (Open Web Text)

Max Activating Token Index: 208

Text #13

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1283. Min Act: -0.1700

Data Index: 7545177 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1356. Min Act: -0.1700

Data Index: 1383824 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1367. Min Act: -0.1700

Data Index: 2691329 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1485. Min Act: -0.1700

Data Index: 8301676 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1319. Min Act: -0.1700

Data Index: 809294 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1288. Min Act: -0.1700

Data Index: 2328881 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1387. Min Act: -0.1700

Data Index: 1529920 (Open Web Text)

Max Activating Token Index: 228