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

Dataset: Open Web Text

Neuron 733 in Layer 1

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: 4.2309. Min Range: -4.2309

Max Act: 4.2309. Min Act: -0.1700

Data Index: 6816667 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.2230. Min Act: -0.1700

Data Index: 6772348 (Open Web Text)

Max Activating Token Index: 189

Text #2

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1972. Min Act: -0.1700

Data Index: 1641151 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1903. Min Act: -0.1700

Data Index: 6784667 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1805. Min Act: -0.1700

Data Index: 1798280 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1665. Min Act: -0.1700

Data Index: 585081 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1527. Min Act: -0.1700

Data Index: 6731349 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1256. Min Act: -0.1700

Data Index: 3684490 (Open Web Text)

Max Activating Token Index: 806

Text #8

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1203. Min Act: -0.1700

Data Index: 1037832 (Open Web Text)

Max Activating Token Index: 163

Text #9

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1220. Min Act: -0.1700

Data Index: 7493153 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1258. Min Act: -0.1700

Data Index: 1599246 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1029. Min Act: -0.1700

Data Index: 3644967 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1164. Min Act: -0.1700

Data Index: 6570718 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1174. Min Act: -0.1700

Data Index: 7220245 (Open Web Text)

Max Activating Token Index: 267

Text #14

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1133. Min Act: -0.1700

Data Index: 6006576 (Open Web Text)

Max Activating Token Index: 407

Text #15

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1085. Min Act: -0.1700

Data Index: 7102210 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.1067. Min Act: -0.1700

Data Index: 3279816 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.0810. Min Act: -0.1700

Data Index: 2214507 (Open Web Text)

Max Activating Token Index: 769

Text #18

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.0735. Min Act: -0.1700

Data Index: 2456925 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 4.2309. Min Range: -4.2309

Max Act: 4.0883. Min Act: -0.1700

Data Index: 6805260 (Open Web Text)

Max Activating Token Index: 501