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

Dataset: Open Web Text

Neuron 1542 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: 3.0559. Min Range: -3.0559

Max Act: 3.0559. Min Act: -0.1700

Data Index: 127724 (Open Web Text)

Max Activating Token Index: 367

Text #1

Max Range: 3.0559. Min Range: -3.0559

Max Act: 3.0201. Min Act: -0.1700

Data Index: 6332288 (Open Web Text)

Max Activating Token Index: 245

Text #2

Max Range: 3.0559. Min Range: -3.0559

Max Act: 3.0184. Min Act: -0.1700

Data Index: 2775189 (Open Web Text)

Max Activating Token Index: 736

Text #3

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9869. Min Act: -0.1700

Data Index: 8208578 (Open Web Text)

Max Activating Token Index: 834

Text #4

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9536. Min Act: -0.1700

Data Index: 1028169 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9283. Min Act: -0.1700

Data Index: 7633215 (Open Web Text)

Max Activating Token Index: 331

Text #6

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9486. Min Act: -0.1700

Data Index: 8136094 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9147. Min Act: -0.1700

Data Index: 688166 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9133. Min Act: -0.1700

Data Index: 6105301 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.9025. Min Act: -0.1700

Data Index: 1897126 (Open Web Text)

Max Activating Token Index: 146

Text #10

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8985. Min Act: -0.1700

Data Index: 8166414 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8624. Min Act: -0.1700

Data Index: 3434020 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8882. Min Act: -0.1700

Data Index: 8286275 (Open Web Text)

Max Activating Token Index: 448

Text #13

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8772. Min Act: -0.1700

Data Index: 4714051 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8621. Min Act: -0.1700

Data Index: 509673 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8652. Min Act: -0.1700

Data Index: 2996463 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8277. Min Act: -0.1700

Data Index: 850367 (Open Web Text)

Max Activating Token Index: 116

Text #17

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8410. Min Act: -0.1700

Data Index: 7790680 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.7990. Min Act: -0.1700

Data Index: 8014269 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 3.0559. Min Range: -3.0559

Max Act: 2.8151. Min Act: -0.1700

Data Index: 7369581 (Open Web Text)

Max Activating Token Index: 877