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

Dataset: Open Web Text

Neuron 1738 in Layer 6

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: 2.7800. Min Range: -2.7800

Max Act: 2.7800. Min Act: -0.1700

Data Index: 3647066 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.7413. Min Act: -0.1700

Data Index: 295340 (Open Web Text)

Max Activating Token Index: 845

Text #2

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.6642. Min Act: -0.1700

Data Index: 7706055 (Open Web Text)

Max Activating Token Index: 757

Text #3

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.6341. Min Act: -0.1700

Data Index: 6655811 (Open Web Text)

Max Activating Token Index: 48

Text #4

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.6437. Min Act: -0.1700

Data Index: 4411059 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.5322. Min Act: -0.1700

Data Index: 4798290 (Open Web Text)

Max Activating Token Index: 202

Text #6

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.5413. Min Act: -0.1700

Data Index: 6948910 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.5348. Min Act: -0.1700

Data Index: 7118391 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.5484. Min Act: -0.1700

Data Index: 380036 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.5308. Min Act: -0.1700

Data Index: 452875 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.5043. Min Act: -0.1700

Data Index: 1631971 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4942. Min Act: -0.1700

Data Index: 1134726 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4594. Min Act: -0.1700

Data Index: 1055851 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4581. Min Act: -0.1700

Data Index: 7812729 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4612. Min Act: -0.1700

Data Index: 3967785 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4429. Min Act: -0.1700

Data Index: 8365781 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4662. Min Act: -0.1700

Data Index: 8643685 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4461. Min Act: -0.1700

Data Index: 7338084 (Open Web Text)

Max Activating Token Index: 914

Text #18

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4521. Min Act: -0.1700

Data Index: 2899655 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 2.7800. Min Range: -2.7800

Max Act: 2.4456. Min Act: -0.1700

Data Index: 4199001 (Open Web Text)

Max Activating Token Index: 382