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

Dataset: Open Web Text

Neuron 1234 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: 4.7709. Min Range: -4.7709

Max Act: 4.7709. Min Act: -0.1700

Data Index: 269745 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7397. Min Act: -0.1700

Data Index: 7386544 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7490. Min Act: -0.1700

Data Index: 4163921 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7354. Min Act: -0.1700

Data Index: 1223161 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7501. Min Act: -0.1700

Data Index: 7319761 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7481. Min Act: -0.1700

Data Index: 6616542 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6820. Min Act: -0.1700

Data Index: 1673635 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6539. Min Act: -0.1700

Data Index: 2938981 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6335. Min Act: -0.1700

Data Index: 1877455 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6413. Min Act: -0.1700

Data Index: 562925 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6151. Min Act: -0.1700

Data Index: 1700968 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6101. Min Act: -0.1700

Data Index: 4158161 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6274. Min Act: -0.1700

Data Index: 8608612 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6134. Min Act: -0.1700

Data Index: 7822615 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6104. Min Act: -0.1700

Data Index: 3196165 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6045. Min Act: -0.1700

Data Index: 5995658 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.5981. Min Act: -0.1700

Data Index: 4741174 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6200. Min Act: -0.1700

Data Index: 3163950 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.5736. Min Act: -0.1700

Data Index: 4051559 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.5880. Min Act: -0.1700

Data Index: 4400470 (Open Web Text)

Max Activating Token Index: 6