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

Dataset: Open Web Text

Neuron 2720 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: 4.5623. Min Range: -4.5623

Max Act: 4.5623. Min Act: -0.1700

Data Index: 7191283 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.5582. Min Act: -0.1700

Data Index: 1985114 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.5042. Min Act: -0.1700

Data Index: 7227306 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4934. Min Act: -0.1700

Data Index: 7614509 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.5092. Min Act: -0.1700

Data Index: 6416372 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4687. Min Act: -0.1700

Data Index: 3287406 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4619. Min Act: -0.1700

Data Index: 5138818 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4229. Min Act: -0.1700

Data Index: 3942259 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4361. Min Act: -0.1700

Data Index: 6626589 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4217. Min Act: -0.1700

Data Index: 1937365 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4334. Min Act: -0.1700

Data Index: 1774935 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4379. Min Act: -0.1700

Data Index: 7954284 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4417. Min Act: -0.1700

Data Index: 1387196 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4388. Min Act: -0.1700

Data Index: 6781966 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4277. Min Act: -0.1700

Data Index: 1762732 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4022. Min Act: -0.1700

Data Index: 6446037 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.3999. Min Act: -0.1700

Data Index: 114490 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.3848. Min Act: -0.1700

Data Index: 5703705 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.4158. Min Act: -0.1700

Data Index: 1996770 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.5623. Min Range: -4.5623

Max Act: 4.3912. Min Act: -0.1700

Data Index: 3279599 (Open Web Text)

Max Activating Token Index: 3