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

Dataset: Open Web Text

Neuron 89 in Layer 0

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: 1.5249. Min Range: -1.5249

Max Act: 1.5249. Min Act: -0.1505

Data Index: 5902980 (Open Web Text)

Max Activating Token Index: 280

Text #1

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4796. Min Act: -0.1667

Data Index: 1703620 (Open Web Text)

Max Activating Token Index: 267

Text #2

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4575. Min Act: -0.1535

Data Index: 3021440 (Open Web Text)

Max Activating Token Index: 676

Text #3

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4610. Min Act: -0.1051

Data Index: 2406149 (Open Web Text)

Max Activating Token Index: 486

Text #4

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4406. Min Act: -0.1266

Data Index: 2587903 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4352. Min Act: -0.1051

Data Index: 4068266 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4294. Min Act: -0.1143

Data Index: 5949591 (Open Web Text)

Max Activating Token Index: 519

Text #7

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4297. Min Act: -0.1144

Data Index: 6778772 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4282. Min Act: -0.1191

Data Index: 6738279 (Open Web Text)

Max Activating Token Index: 740

Text #9

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4211. Min Act: -0.1465

Data Index: 5064352 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4125. Min Act: -0.1051

Data Index: 7391204 (Open Web Text)

Max Activating Token Index: 1010

Text #11

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4092. Min Act: -0.1343

Data Index: 7989197 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4106. Min Act: -0.1271

Data Index: 6277743 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4144. Min Act: -0.1493

Data Index: 4659993 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4149. Min Act: -0.1131

Data Index: 1703619 (Open Web Text)

Max Activating Token Index: 863

Text #15

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4187. Min Act: -0.1560

Data Index: 4733263 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4169. Min Act: -0.1228

Data Index: 7821734 (Open Web Text)

Max Activating Token Index: 267

Text #17

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4039. Min Act: -0.1278

Data Index: 2158072 (Open Web Text)

Max Activating Token Index: 587

Text #18

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4064. Min Act: -0.1156

Data Index: 4769656 (Open Web Text)

Max Activating Token Index: 738

Text #19

Max Range: 1.5249. Min Range: -1.5249

Max Act: 1.4079. Min Act: -0.1051

Data Index: 1437985 (Open Web Text)

Max Activating Token Index: 266