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

Dataset: Open Web Text

Neuron 721 in Layer 2

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: 4.2940. Min Range: -4.2940

Max Act: 4.2940. Min Act: -0.1700

Data Index: 1160597 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.2426. Min Act: -0.1700

Data Index: 6794011 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.2259. Min Act: -0.1700

Data Index: 7294261 (Open Web Text)

Max Activating Token Index: 959

Text #3

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1201. Min Act: -0.1700

Data Index: 7053519 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1242. Min Act: -0.1700

Data Index: 2918404 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1284. Min Act: -0.1700

Data Index: 6360016 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1442. Min Act: -0.1700

Data Index: 1108335 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1670. Min Act: -0.1700

Data Index: 961375 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1163. Min Act: -0.1700

Data Index: 6469953 (Open Web Text)

Max Activating Token Index: 967

Text #9

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1452. Min Act: -0.1700

Data Index: 6422436 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1286. Min Act: -0.1700

Data Index: 4164483 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1598. Min Act: -0.1700

Data Index: 5379719 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.2061. Min Act: -0.1700

Data Index: 7562224 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1044. Min Act: -0.1700

Data Index: 5797430 (Open Web Text)

Max Activating Token Index: 856

Text #14

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.0738. Min Act: -0.1700

Data Index: 8393953 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.0795. Min Act: -0.1700

Data Index: 6224614 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1062. Min Act: -0.1700

Data Index: 8698396 (Open Web Text)

Max Activating Token Index: 773

Text #17

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1209. Min Act: -0.1700

Data Index: 5233326 (Open Web Text)

Max Activating Token Index: 1000

Text #18

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1035. Min Act: -0.1700

Data Index: 1019698 (Open Web Text)

Max Activating Token Index: 141

Text #19

Max Range: 4.2940. Min Range: -4.2940

Max Act: 4.1138. Min Act: -0.1700

Data Index: 6632300 (Open Web Text)

Max Activating Token Index: 419