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

Dataset: Open Web Text

Neuron 1587 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: 0.6648. Min Range: -0.6648

Max Act: 0.6648. Min Act: -0.1700

Data Index: 6352172 (Open Web Text)

Max Activating Token Index: 319

Text #1

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6573. Min Act: -0.1700

Data Index: 975019 (Open Web Text)

Max Activating Token Index: 322

Text #2

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6394. Min Act: -0.1700

Data Index: 5444729 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6264. Min Act: -0.1700

Data Index: 8546521 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6097. Min Act: -0.1700

Data Index: 1791653 (Open Web Text)

Max Activating Token Index: 309

Text #5

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6113. Min Act: -0.1700

Data Index: 578496 (Open Web Text)

Max Activating Token Index: 317

Text #6

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5948. Min Act: -0.1700

Data Index: 1757862 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6012. Min Act: -0.1700

Data Index: 5514077 (Open Web Text)

Max Activating Token Index: 305

Text #8

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6003. Min Act: -0.1700

Data Index: 2313076 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5986. Min Act: -0.1700

Data Index: 1374018 (Open Web Text)

Max Activating Token Index: 305

Text #10

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5947. Min Act: -0.1700

Data Index: 6413637 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6024. Min Act: -0.1700

Data Index: 6800076 (Open Web Text)

Max Activating Token Index: 321

Text #12

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5992. Min Act: -0.1700

Data Index: 4954454 (Open Web Text)

Max Activating Token Index: 299

Text #13

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5964. Min Act: -0.1700

Data Index: 6610551 (Open Web Text)

Max Activating Token Index: 898

Text #14

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5958. Min Act: -0.1700

Data Index: 1791650 (Open Web Text)

Max Activating Token Index: 292

Text #15

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5879. Min Act: -0.1700

Data Index: 4065089 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5923. Min Act: -0.1700

Data Index: 1066427 (Open Web Text)

Max Activating Token Index: 300

Text #17

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5848. Min Act: -0.1700

Data Index: 5244826 (Open Web Text)

Max Activating Token Index: 293

Text #18

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5904. Min Act: -0.1700

Data Index: 3131791 (Open Web Text)

Max Activating Token Index: 309

Text #19

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5843. Min Act: -0.1700

Data Index: 6094695 (Open Web Text)

Max Activating Token Index: 312