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

Dataset: Open Web Text

Neuron 30 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: 2.9105. Min Range: -2.9105

Max Act: 2.9076. Min Act: -0.1700

Data Index: 6743414 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.9029. Min Act: -0.1700

Data Index: 6718301 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.9105. Min Act: -0.1700

Data Index: 7639279 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8828. Min Act: -0.1700

Data Index: 4876987 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8756. Min Act: -0.1700

Data Index: 4859292 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8785. Min Act: -0.1700

Data Index: 2411259 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8810. Min Act: -0.1700

Data Index: 6646999 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8745. Min Act: -0.1700

Data Index: 7575408 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8691. Min Act: -0.1700

Data Index: 8457612 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8640. Min Act: -0.1700

Data Index: 1609676 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8689. Min Act: -0.1700

Data Index: 8448432 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8389. Min Act: -0.1700

Data Index: 1432132 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8500. Min Act: -0.1700

Data Index: 6646998 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8372. Min Act: -0.1700

Data Index: 730249 (Open Web Text)

Max Activating Token Index: 669

Text #14

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8506. Min Act: -0.1700

Data Index: 6646995 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8401. Min Act: -0.1700

Data Index: 8825567 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8437. Min Act: -0.1700

Data Index: 6673193 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8485. Min Act: -0.1700

Data Index: 1742872 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8351. Min Act: -0.1700

Data Index: 4137850 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9105. Min Range: -2.9105

Max Act: 2.8271. Min Act: -0.1700

Data Index: 3401967 (Open Web Text)

Max Activating Token Index: 3