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

Dataset: Open Web Text

Neuron 2527 in Layer 5

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: 3.4195. Min Range: -3.4195

Max Act: 3.4195. Min Act: -0.1700

Data Index: 4961884 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.3998. Min Act: -0.1700

Data Index: 7530878 (Open Web Text)

Max Activating Token Index: 720

Text #2

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1854133 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.3060. Min Act: -0.1700

Data Index: 4142041 (Open Web Text)

Max Activating Token Index: 64

Text #4

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2856. Min Act: -0.1700

Data Index: 544610 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2802. Min Act: -0.1700

Data Index: 7161698 (Open Web Text)

Max Activating Token Index: 327

Text #6

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2859. Min Act: -0.1700

Data Index: 8618995 (Open Web Text)

Max Activating Token Index: 663

Text #7

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2461. Min Act: -0.1700

Data Index: 7831394 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2359. Min Act: -0.1700

Data Index: 3208061 (Open Web Text)

Max Activating Token Index: 377

Text #9

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2191. Min Act: -0.1700

Data Index: 7777859 (Open Web Text)

Max Activating Token Index: 503

Text #10

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2079. Min Act: -0.1700

Data Index: 6285271 (Open Web Text)

Max Activating Token Index: 291

Text #11

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.1951. Min Act: -0.1700

Data Index: 2298106 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2023. Min Act: -0.1700

Data Index: 4615093 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.2142. Min Act: -0.1700

Data Index: 167841 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.1870. Min Act: -0.1700

Data Index: 6600015 (Open Web Text)

Max Activating Token Index: 502

Text #15

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.1884. Min Act: -0.1700

Data Index: 5593215 (Open Web Text)

Max Activating Token Index: 973

Text #16

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.1666. Min Act: -0.1700

Data Index: 8749191 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.1910. Min Act: -0.1700

Data Index: 3003859 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.1634. Min Act: -0.1700

Data Index: 4304803 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 3.4195. Min Range: -3.4195

Max Act: 3.1749. Min Act: -0.1700

Data Index: 2979806 (Open Web Text)

Max Activating Token Index: 559