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

Dataset: Open Web Text

Neuron 1155 in Layer 5

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: 6.3375. Min Range: -6.3375

Max Act: 6.3375. Min Act: -0.1700

Data Index: 2315333 (Open Web Text)

Max Activating Token Index: 531

Text #1

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2661. Min Act: -0.1700

Data Index: 1663085 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2309. Min Act: -0.1700

Data Index: 2892420 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2407. Min Act: -0.1700

Data Index: 2470164 (Open Web Text)

Max Activating Token Index: 284

Text #4

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2522. Min Act: -0.1700

Data Index: 4336282 (Open Web Text)

Max Activating Token Index: 141

Text #5

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2882. Min Act: -0.1700

Data Index: 471248 (Open Web Text)

Max Activating Token Index: 291

Text #6

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2779. Min Act: -0.1700

Data Index: 4117697 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2332. Min Act: -0.1700

Data Index: 1827872 (Open Web Text)

Max Activating Token Index: 580

Text #8

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2275. Min Act: -0.1700

Data Index: 5336201 (Open Web Text)

Max Activating Token Index: 629

Text #9

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1951. Min Act: -0.1700

Data Index: 8180861 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2110. Min Act: -0.1700

Data Index: 4015368 (Open Web Text)

Max Activating Token Index: 920

Text #11

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.2135. Min Act: -0.1700

Data Index: 7577265 (Open Web Text)

Max Activating Token Index: 277

Text #12

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1624. Min Act: -0.1697

Data Index: 2148422 (Open Web Text)

Max Activating Token Index: 999

Text #13

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1988. Min Act: -0.1700

Data Index: 3975036 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1871. Min Act: -0.1700

Data Index: 6456148 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1836. Min Act: -0.1700

Data Index: 5403375 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1708. Min Act: -0.1700

Data Index: 2657766 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1532. Min Act: -0.1700

Data Index: 690319 (Open Web Text)

Max Activating Token Index: 699

Text #18

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1660. Min Act: -0.1700

Data Index: 6098950 (Open Web Text)

Max Activating Token Index: 262

Text #19

Max Range: 6.3375. Min Range: -6.3375

Max Act: 6.1401. Min Act: -0.1700

Data Index: 4992527 (Open Web Text)

Max Activating Token Index: 592