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

Dataset: Open Web Text

Neuron 414 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: 2.2437. Min Range: -2.2437

Max Act: 2.2437. Min Act: -0.1700

Data Index: 1740353 (Open Web Text)

Max Activating Token Index: 793

Text #1

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.2089. Min Act: -0.1699

Data Index: 751393 (Open Web Text)

Max Activating Token Index: 793

Text #2

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.2218. Min Act: -0.1700

Data Index: 1740354 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1579. Min Act: -0.1700

Data Index: 8457723 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1531. Min Act: -0.1700

Data Index: 1204983 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1420. Min Act: -0.1700

Data Index: 7558556 (Open Web Text)

Max Activating Token Index: 767

Text #6

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1263. Min Act: -0.1700

Data Index: 2185838 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1359. Min Act: -0.1700

Data Index: 6981299 (Open Web Text)

Max Activating Token Index: 131

Text #8

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1275. Min Act: -0.1700

Data Index: 7880074 (Open Web Text)

Max Activating Token Index: 954

Text #9

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1350. Min Act: -0.1700

Data Index: 5159186 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1270. Min Act: -0.1700

Data Index: 2073746 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1424. Min Act: -0.1700

Data Index: 2674317 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1257. Min Act: -0.1700

Data Index: 5146351 (Open Web Text)

Max Activating Token Index: 1004

Text #13

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1148. Min Act: -0.1700

Data Index: 7977976 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1147. Min Act: -0.1700

Data Index: 4657904 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1216. Min Act: -0.1699

Data Index: 7379790 (Open Web Text)

Max Activating Token Index: 694

Text #16

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1160. Min Act: -0.1700

Data Index: 3210768 (Open Web Text)

Max Activating Token Index: 954

Text #17

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1233. Min Act: -0.1700

Data Index: 2770273 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1096. Min Act: -0.1700

Data Index: 6609157 (Open Web Text)

Max Activating Token Index: 788

Text #19

Max Range: 2.2437. Min Range: -2.2437

Max Act: 2.1054. Min Act: -0.1700

Data Index: 4001446 (Open Web Text)

Max Activating Token Index: 970