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

Dataset: Open Web Text

Neuron 1014 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: 3.8305. Min Range: -3.8305

Max Act: 3.8305. Min Act: -0.1700

Data Index: 5284906 (Open Web Text)

Max Activating Token Index: 239

Text #1

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.8017. Min Act: -0.1700

Data Index: 3133946 (Open Web Text)

Max Activating Token Index: 712

Text #2

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.7862. Min Act: -0.1700

Data Index: 6031437 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.8017. Min Act: -0.1700

Data Index: 7523204 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.7322. Min Act: -0.1700

Data Index: 1332906 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.7227. Min Act: -0.1700

Data Index: 1280011 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.7213. Min Act: -0.1700

Data Index: 2023943 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.7277. Min Act: -0.1700

Data Index: 7662363 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6822. Min Act: -0.1700

Data Index: 7154520 (Open Web Text)

Max Activating Token Index: 588

Text #9

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6907. Min Act: -0.1700

Data Index: 3133947 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6934. Min Act: -0.1700

Data Index: 3389382 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6422. Min Act: -0.1700

Data Index: 2219222 (Open Web Text)

Max Activating Token Index: 288

Text #12

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6566. Min Act: -0.1700

Data Index: 2867834 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6446. Min Act: -0.1700

Data Index: 1179448 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6253. Min Act: -0.1700

Data Index: 641841 (Open Web Text)

Max Activating Token Index: 180

Text #15

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6515. Min Act: -0.1700

Data Index: 4348152 (Open Web Text)

Max Activating Token Index: 846

Text #16

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6259. Min Act: -0.1700

Data Index: 7154890 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6144. Min Act: -0.1700

Data Index: 3769867 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6434. Min Act: -0.1700

Data Index: 3133944 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 3.8305. Min Range: -3.8305

Max Act: 3.6038. Min Act: -0.1700

Data Index: 6924599 (Open Web Text)

Max Activating Token Index: 139