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

Dataset: Open Web Text

Neuron 1579 in Layer 4

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: 3.8861. Min Range: -3.8861

Max Act: 3.8829. Min Act: -0.1700

Data Index: 1528340 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8861. Min Act: -0.1700

Data Index: 1730564 (Open Web Text)

Max Activating Token Index: 563

Text #2

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8766. Min Act: -0.1700

Data Index: 8474198 (Open Web Text)

Max Activating Token Index: 173

Text #3

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8797. Min Act: -0.1700

Data Index: 5431830 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8358. Min Act: -0.1700

Data Index: 8232313 (Open Web Text)

Max Activating Token Index: 172

Text #5

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8251. Min Act: -0.1700

Data Index: 8232298 (Open Web Text)

Max Activating Token Index: 241

Text #6

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8533. Min Act: -0.1700

Data Index: 1011507 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8281. Min Act: -0.1700

Data Index: 4792058 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8388. Min Act: -0.1700

Data Index: 8474181 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8086. Min Act: -0.1700

Data Index: 8474173 (Open Web Text)

Max Activating Token Index: 423

Text #10

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7826. Min Act: -0.1700

Data Index: 8598500 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7870. Min Act: -0.1700

Data Index: 8232309 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7787. Min Act: -0.1700

Data Index: 1011501 (Open Web Text)

Max Activating Token Index: 424

Text #13

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7870. Min Act: -0.1700

Data Index: 5431832 (Open Web Text)

Max Activating Token Index: 100

Text #14

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7606. Min Act: -0.1700

Data Index: 4792051 (Open Web Text)

Max Activating Token Index: 78

Text #15

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7805. Min Act: -0.1700

Data Index: 8474189 (Open Web Text)

Max Activating Token Index: 173

Text #16

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7786. Min Act: -0.1700

Data Index: 6006894 (Open Web Text)

Max Activating Token Index: 43

Text #17

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7282. Min Act: -0.1700

Data Index: 4811740 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7620. Min Act: -0.1700

Data Index: 8474184 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7388. Min Act: -0.1700

Data Index: 3292833 (Open Web Text)

Max Activating Token Index: 219