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

Dataset: Open Web Text

Neuron 677 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: 1.0333. Min Range: -1.0333

Max Act: 1.0333. Min Act: -0.1700

Data Index: 4789893 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0202. Min Act: -0.1700

Data Index: 231954 (Open Web Text)

Max Activating Token Index: 966

Text #2

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0182. Min Act: -0.1700

Data Index: 106195 (Open Web Text)

Max Activating Token Index: 108

Text #3

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0165. Min Act: -0.1501

Data Index: 8761106 (Open Web Text)

Max Activating Token Index: 210

Text #4

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0173. Min Act: -0.1691

Data Index: 418024 (Open Web Text)

Max Activating Token Index: 105

Text #5

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0083. Min Act: -0.1628

Data Index: 8586616 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0086. Min Act: -0.1609

Data Index: 5189777 (Open Web Text)

Max Activating Token Index: 277

Text #7

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0060. Min Act: -0.1637

Data Index: 5174322 (Open Web Text)

Max Activating Token Index: 618

Text #8

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0065. Min Act: -0.1573

Data Index: 8266043 (Open Web Text)

Max Activating Token Index: 338

Text #9

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0008. Min Act: -0.1698

Data Index: 7741522 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9960. Min Act: -0.1700

Data Index: 283916 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9943. Min Act: -0.1700

Data Index: 3509620 (Open Web Text)

Max Activating Token Index: 308

Text #12

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0008. Min Act: -0.1644

Data Index: 2656982 (Open Web Text)

Max Activating Token Index: 541

Text #13

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9887. Min Act: -0.1684

Data Index: 8338213 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9926. Min Act: -0.1655

Data Index: 565429 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9932. Min Act: -0.1691

Data Index: 6495696 (Open Web Text)

Max Activating Token Index: 597

Text #16

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9907. Min Act: -0.1615

Data Index: 6110033 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9887. Min Act: -0.1698

Data Index: 5498999 (Open Web Text)

Max Activating Token Index: 109

Text #18

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9764. Min Act: -0.1699

Data Index: 1336541 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9853. Min Act: -0.1676

Data Index: 1619623 (Open Web Text)

Max Activating Token Index: 394