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

Dataset: Open Web Text

Neuron 1699 in Layer 1

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: 1.6960. Min Range: -1.6960

Max Act: 1.6960. Min Act: -0.1700

Data Index: 4884883 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6656. Min Act: -0.1700

Data Index: 4067914 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6496. Min Act: -0.1700

Data Index: 5143473 (Open Web Text)

Max Activating Token Index: 593

Text #3

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6549. Min Act: -0.1700

Data Index: 6324902 (Open Web Text)

Max Activating Token Index: 416

Text #4

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6419. Min Act: -0.1700

Data Index: 6338520 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6411. Min Act: -0.1700

Data Index: 756562 (Open Web Text)

Max Activating Token Index: 73

Text #6

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6441. Min Act: -0.1700

Data Index: 1937253 (Open Web Text)

Max Activating Token Index: 43

Text #7

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6202. Min Act: -0.1700

Data Index: 6370201 (Open Web Text)

Max Activating Token Index: 441

Text #8

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6197. Min Act: -0.1700

Data Index: 7913184 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6191. Min Act: -0.1700

Data Index: 2857249 (Open Web Text)

Max Activating Token Index: 146

Text #10

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6048. Min Act: -0.1700

Data Index: 8644177 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6063. Min Act: -0.1700

Data Index: 6536856 (Open Web Text)

Max Activating Token Index: 485

Text #12

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6055. Min Act: -0.1700

Data Index: 7475383 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.5998. Min Act: -0.1700

Data Index: 1357848 (Open Web Text)

Max Activating Token Index: 709

Text #14

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.5913. Min Act: -0.1700

Data Index: 8502893 (Open Web Text)

Max Activating Token Index: 941

Text #15

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.5894. Min Act: -0.1700

Data Index: 4625531 (Open Web Text)

Max Activating Token Index: 374

Text #16

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.5925. Min Act: -0.1700

Data Index: 6430135 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.5896. Min Act: -0.1700

Data Index: 1311687 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.5864. Min Act: -0.1700

Data Index: 1905733 (Open Web Text)

Max Activating Token Index: 399

Text #19

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.5844. Min Act: -0.1700

Data Index: 8471428 (Open Web Text)

Max Activating Token Index: 397