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

Dataset: Open Web Text

Neuron 953 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: 2.8683. Min Range: -2.8683

Max Act: 2.8683. Min Act: -0.1700

Data Index: 4664520 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.8057. Min Act: -0.1700

Data Index: 7000396 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.8118. Min Act: -0.1700

Data Index: 828422 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7823. Min Act: -0.1700

Data Index: 4715115 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7919. Min Act: -0.1700

Data Index: 117546 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7692. Min Act: -0.1700

Data Index: 1819819 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7653. Min Act: -0.1700

Data Index: 6361867 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7490. Min Act: -0.1700

Data Index: 7320051 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7480. Min Act: -0.1700

Data Index: 798601 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7648. Min Act: -0.1700

Data Index: 5861111 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7548. Min Act: -0.1700

Data Index: 8554162 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7389. Min Act: -0.1700

Data Index: 3148018 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7361. Min Act: -0.1700

Data Index: 1491380 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7473. Min Act: -0.1700

Data Index: 8773291 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7436. Min Act: -0.1700

Data Index: 8761264 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7381. Min Act: -0.1700

Data Index: 2109357 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7389. Min Act: -0.1700

Data Index: 4108261 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7429. Min Act: -0.1700

Data Index: 8251198 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7528. Min Act: -0.1700

Data Index: 4722598 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.7217. Min Act: -0.1700

Data Index: 526246 (Open Web Text)

Max Activating Token Index: 2