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

Dataset: Open Web Text

Neuron 2251 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: 1.3365. Min Range: -1.3365

Max Act: 1.3316. Min Act: -0.1700

Data Index: 6650958 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3365. Min Act: -0.1700

Data Index: 2604136 (Open Web Text)

Max Activating Token Index: 332

Text #2

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3109. Min Act: -0.1700

Data Index: 6097853 (Open Web Text)

Max Activating Token Index: 334

Text #3

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3085. Min Act: -0.1700

Data Index: 4725966 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3200. Min Act: -0.1700

Data Index: 7442229 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3093. Min Act: -0.1700

Data Index: 6643167 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.3002. Min Act: -0.1700

Data Index: 1970327 (Open Web Text)

Max Activating Token Index: 944

Text #7

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2979. Min Act: -0.1700

Data Index: 4206894 (Open Web Text)

Max Activating Token Index: 81

Text #8

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2981. Min Act: -0.1700

Data Index: 5295915 (Open Web Text)

Max Activating Token Index: 381

Text #9

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2998. Min Act: -0.1700

Data Index: 1811685 (Open Web Text)

Max Activating Token Index: 956

Text #10

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2929. Min Act: -0.1700

Data Index: 2147978 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2901. Min Act: -0.1700

Data Index: 6022382 (Open Web Text)

Max Activating Token Index: 936

Text #12

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2945. Min Act: -0.1700

Data Index: 3892515 (Open Web Text)

Max Activating Token Index: 800

Text #13

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2876. Min Act: -0.1700

Data Index: 5464215 (Open Web Text)

Max Activating Token Index: 219

Text #14

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2828. Min Act: -0.1700

Data Index: 1496679 (Open Web Text)

Max Activating Token Index: 210

Text #15

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2989. Min Act: -0.1700

Data Index: 1155776 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2844. Min Act: -0.1700

Data Index: 3377954 (Open Web Text)

Max Activating Token Index: 301

Text #17

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2812. Min Act: -0.1700

Data Index: 5544919 (Open Web Text)

Max Activating Token Index: 176

Text #18

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2826. Min Act: -0.1700

Data Index: 2945508 (Open Web Text)

Max Activating Token Index: 273

Text #19

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2578. Min Act: -0.1700

Data Index: 3585300 (Open Web Text)

Max Activating Token Index: 960