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

Dataset: Open Web Text

Neuron 2884 in Layer 3

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: 3.2457. Min Range: -3.2457

Max Act: 3.2457. Min Act: -0.1700

Data Index: 2769475 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1975. Min Act: -0.1700

Data Index: 2922514 (Open Web Text)

Max Activating Token Index: 652

Text #2

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.2043. Min Act: -0.1700

Data Index: 6707405 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1658. Min Act: -0.1700

Data Index: 6974252 (Open Web Text)

Max Activating Token Index: 180

Text #4

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1494. Min Act: -0.1700

Data Index: 4248895 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1299. Min Act: -0.1700

Data Index: 1429195 (Open Web Text)

Max Activating Token Index: 307

Text #6

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1312. Min Act: -0.1700

Data Index: 7187737 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1367. Min Act: -0.1700

Data Index: 7637132 (Open Web Text)

Max Activating Token Index: 369

Text #8

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1779. Min Act: -0.1700

Data Index: 7981825 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1220. Min Act: -0.1700

Data Index: 1917474 (Open Web Text)

Max Activating Token Index: 209

Text #10

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1600. Min Act: -0.1700

Data Index: 2043456 (Open Web Text)

Max Activating Token Index: 861

Text #11

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0925. Min Act: -0.1700

Data Index: 4688040 (Open Web Text)

Max Activating Token Index: 788

Text #12

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1150. Min Act: -0.1700

Data Index: 3220866 (Open Web Text)

Max Activating Token Index: 121

Text #13

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1217. Min Act: -0.1700

Data Index: 1403261 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0345. Min Act: -0.1700

Data Index: 1137849 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1079. Min Act: -0.1700

Data Index: 1038710 (Open Web Text)

Max Activating Token Index: 77

Text #16

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.1064. Min Act: -0.1700

Data Index: 7498271 (Open Web Text)

Max Activating Token Index: 83

Text #17

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0995. Min Act: -0.1700

Data Index: 4388767 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0372. Min Act: -0.1700

Data Index: 4340649 (Open Web Text)

Max Activating Token Index: 492

Text #19

Max Range: 3.2457. Min Range: -3.2457

Max Act: 3.0792. Min Act: -0.1700

Data Index: 526456 (Open Web Text)

Max Activating Token Index: 153