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

Dataset: Open Web Text

Neuron 2400 in Layer 6

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: 3.3493. Min Range: -3.3493

Max Act: 3.3493. Min Act: -0.1700

Data Index: 6241534 (Open Web Text)

Max Activating Token Index: 64

Text #1

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2759. Min Act: -0.1700

Data Index: 5971331 (Open Web Text)

Max Activating Token Index: 218

Text #2

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2609. Min Act: -0.1700

Data Index: 1263913 (Open Web Text)

Max Activating Token Index: 345

Text #3

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2611. Min Act: -0.1700

Data Index: 7561249 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2328. Min Act: -0.1700

Data Index: 1569478 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2525. Min Act: -0.1700

Data Index: 615804 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2081. Min Act: -0.1700

Data Index: 1853327 (Open Web Text)

Max Activating Token Index: 841

Text #7

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2335. Min Act: -0.1700

Data Index: 8489208 (Open Web Text)

Max Activating Token Index: 280

Text #8

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1971. Min Act: -0.1700

Data Index: 6635481 (Open Web Text)

Max Activating Token Index: 956

Text #9

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2065. Min Act: -0.1700

Data Index: 1263911 (Open Web Text)

Max Activating Token Index: 82

Text #10

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1830. Min Act: -0.1700

Data Index: 509037 (Open Web Text)

Max Activating Token Index: 342

Text #11

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1965. Min Act: -0.1700

Data Index: 109556 (Open Web Text)

Max Activating Token Index: 952

Text #12

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1913. Min Act: -0.1700

Data Index: 7489783 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1914. Min Act: -0.1700

Data Index: 8465837 (Open Web Text)

Max Activating Token Index: 167

Text #14

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.2136. Min Act: -0.1700

Data Index: 3938344 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1994. Min Act: -0.1700

Data Index: 2966333 (Open Web Text)

Max Activating Token Index: 800

Text #16

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1639. Min Act: -0.1700

Data Index: 1260710 (Open Web Text)

Max Activating Token Index: 634

Text #17

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1776. Min Act: -0.1700

Data Index: 5975926 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1837. Min Act: -0.1700

Data Index: 3876519 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.3493. Min Range: -3.3493

Max Act: 3.1652. Min Act: -0.1700

Data Index: 27316 (Open Web Text)

Max Activating Token Index: 538