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

Dataset: Open Web Text

Neuron 344 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: 3.0748. Min Range: -3.0748

Max Act: 3.0748. Min Act: -0.1700

Data Index: 5494590 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.9687. Min Act: -0.1700

Data Index: 989711 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.9518. Min Act: -0.1700

Data Index: 7317410 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.9553. Min Act: -0.1700

Data Index: 4179846 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.9106. Min Act: -0.1700

Data Index: 7118495 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.9001. Min Act: -0.1700

Data Index: 8539592 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.9147. Min Act: -0.1700

Data Index: 6955790 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.9075. Min Act: -0.1700

Data Index: 2496539 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8976. Min Act: -0.1700

Data Index: 7539710 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8862. Min Act: -0.1700

Data Index: 1223060 (Open Web Text)

Max Activating Token Index: 330

Text #10

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8696. Min Act: -0.1700

Data Index: 5435117 (Open Web Text)

Max Activating Token Index: 59

Text #11

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8614. Min Act: -0.1700

Data Index: 3129548 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8603. Min Act: -0.1700

Data Index: 3552053 (Open Web Text)

Max Activating Token Index: 53

Text #13

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8558. Min Act: -0.1700

Data Index: 4444877 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8620. Min Act: -0.1700

Data Index: 4367113 (Open Web Text)

Max Activating Token Index: 479

Text #15

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8580. Min Act: -0.1700

Data Index: 101867 (Open Web Text)

Max Activating Token Index: 260

Text #16

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8650. Min Act: -0.1700

Data Index: 4643423 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8515. Min Act: -0.1700

Data Index: 383569 (Open Web Text)

Max Activating Token Index: 917

Text #18

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8310. Min Act: -0.1700

Data Index: 6796741 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 3.0748. Min Range: -3.0748

Max Act: 2.8392. Min Act: -0.1700

Data Index: 6168061 (Open Web Text)

Max Activating Token Index: 5