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

Dataset: Open Web Text

Neuron 1065 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: 3.0675. Min Range: -3.0675

Max Act: 3.0675. Min Act: -0.1700

Data Index: 6307999 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9962. Min Act: -0.1700

Data Index: 8503894 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9977. Min Act: -0.1700

Data Index: 8054462 (Open Web Text)

Max Activating Token Index: 272

Text #3

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9474. Min Act: -0.1700

Data Index: 7301002 (Open Web Text)

Max Activating Token Index: 685

Text #4

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9316. Min Act: -0.1700

Data Index: 2502544 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9490. Min Act: -0.1700

Data Index: 8572887 (Open Web Text)

Max Activating Token Index: 239

Text #6

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9401. Min Act: -0.1700

Data Index: 2662088 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9240. Min Act: -0.1700

Data Index: 4265554 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9034. Min Act: -0.1700

Data Index: 4929378 (Open Web Text)

Max Activating Token Index: 346

Text #9

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9234. Min Act: -0.1700

Data Index: 8572075 (Open Web Text)

Max Activating Token Index: 932

Text #10

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9024. Min Act: -0.1700

Data Index: 1743945 (Open Web Text)

Max Activating Token Index: 714

Text #11

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9056. Min Act: -0.1700

Data Index: 4804967 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9132. Min Act: -0.1700

Data Index: 7203509 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.8957. Min Act: -0.1700

Data Index: 3520769 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.8841. Min Act: -0.1700

Data Index: 3633462 (Open Web Text)

Max Activating Token Index: 799

Text #15

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.9049. Min Act: -0.1700

Data Index: 6976316 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.8931. Min Act: -0.1700

Data Index: 4120500 (Open Web Text)

Max Activating Token Index: 214

Text #17

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.8638. Min Act: -0.1700

Data Index: 167407 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.8689. Min Act: -0.1700

Data Index: 4032932 (Open Web Text)

Max Activating Token Index: 1010

Text #19

Max Range: 3.0675. Min Range: -3.0675

Max Act: 2.8652. Min Act: -0.1700

Data Index: 1999037 (Open Web Text)

Max Activating Token Index: 579