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

Dataset: Open Web Text

Neuron 3039 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: 1.9022. Min Range: -1.9022

Max Act: 1.9022. Min Act: -0.1700

Data Index: 7545839 (Open Web Text)

Max Activating Token Index: 298

Text #1

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8990. Min Act: -0.1700

Data Index: 8014339 (Open Web Text)

Max Activating Token Index: 459

Text #2

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8762. Min Act: -0.1700

Data Index: 7633719 (Open Web Text)

Max Activating Token Index: 122

Text #3

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8734. Min Act: -0.1699

Data Index: 4653634 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8591. Min Act: -0.1698

Data Index: 7640167 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8552. Min Act: -0.1700

Data Index: 7020657 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8593. Min Act: -0.1699

Data Index: 1102572 (Open Web Text)

Max Activating Token Index: 313

Text #7

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8650. Min Act: -0.1700

Data Index: 7722402 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8575. Min Act: -0.1700

Data Index: 6661678 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8701. Min Act: -0.1700

Data Index: 7647656 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8594. Min Act: -0.1700

Data Index: 463561 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8634. Min Act: -0.1698

Data Index: 6072623 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8661. Min Act: -0.1700

Data Index: 7395425 (Open Web Text)

Max Activating Token Index: 180

Text #13

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8576. Min Act: -0.1699

Data Index: 5509521 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8682. Min Act: -0.1700

Data Index: 7217411 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8562. Min Act: -0.1700

Data Index: 2459291 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8419. Min Act: -0.1700

Data Index: 2678342 (Open Web Text)

Max Activating Token Index: 761

Text #17

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8603. Min Act: -0.1700

Data Index: 17529 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8578. Min Act: -0.1700

Data Index: 4933171 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 1.9022. Min Range: -1.9022

Max Act: 1.8552. Min Act: -0.1700

Data Index: 8418335 (Open Web Text)

Max Activating Token Index: 1014