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

Dataset: Open Web Text

Neuron 1344 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: 3.3650. Min Range: -3.3650

Max Act: 3.3650. Min Act: -0.1700

Data Index: 6926141 (Open Web Text)

Max Activating Token Index: 328

Text #1

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2825. Min Act: -0.1700

Data Index: 4478581 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2306. Min Act: -0.1700

Data Index: 1197239 (Open Web Text)

Max Activating Token Index: 515

Text #3

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2476. Min Act: -0.1700

Data Index: 2335272 (Open Web Text)

Max Activating Token Index: 292

Text #4

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2110. Min Act: -0.1700

Data Index: 2406946 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2240. Min Act: -0.1700

Data Index: 2406957 (Open Web Text)

Max Activating Token Index: 390

Text #6

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.2130. Min Act: -0.1700

Data Index: 1768736 (Open Web Text)

Max Activating Token Index: 305

Text #7

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1599. Min Act: -0.1700

Data Index: 7945601 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1247. Min Act: -0.1700

Data Index: 8746721 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1360. Min Act: -0.1700

Data Index: 8502307 (Open Web Text)

Max Activating Token Index: 263

Text #10

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1318. Min Act: -0.1700

Data Index: 5128012 (Open Web Text)

Max Activating Token Index: 310

Text #11

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1344. Min Act: -0.1700

Data Index: 4306197 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1344. Min Act: -0.1700

Data Index: 8818924 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1266. Min Act: -0.1700

Data Index: 38571 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1036. Min Act: -0.1700

Data Index: 3106318 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.1106. Min Act: -0.1700

Data Index: 7301446 (Open Web Text)

Max Activating Token Index: 960

Text #16

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.0984. Min Act: -0.1700

Data Index: 7824649 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.0960. Min Act: -0.1700

Data Index: 1315956 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.0692. Min Act: -0.1700

Data Index: 820080 (Open Web Text)

Max Activating Token Index: 993

Text #19

Max Range: 3.3650. Min Range: -3.3650

Max Act: 3.0832. Min Act: -0.1700

Data Index: 7114435 (Open Web Text)

Max Activating Token Index: 310