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

Dataset: Open Web Text

Neuron 487 in Layer 3

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: 4.7328. Min Range: -4.7328

Max Act: 4.7328. Min Act: -0.1700

Data Index: 3626211 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.6880. Min Act: -0.1700

Data Index: 3263314 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.5183. Min Act: -0.1700

Data Index: 7480980 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4902. Min Act: -0.1700

Data Index: 5454954 (Open Web Text)

Max Activating Token Index: 758

Text #4

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.5153. Min Act: -0.1700

Data Index: 8261916 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4718. Min Act: -0.1700

Data Index: 6484201 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4487. Min Act: -0.1700

Data Index: 7583411 (Open Web Text)

Max Activating Token Index: 239

Text #7

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4319. Min Act: -0.1700

Data Index: 5427876 (Open Web Text)

Max Activating Token Index: 450

Text #8

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4730. Min Act: -0.1700

Data Index: 7593180 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4542. Min Act: -0.1700

Data Index: 5854219 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4465. Min Act: -0.1700

Data Index: 6459955 (Open Web Text)

Max Activating Token Index: 82

Text #11

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4471. Min Act: -0.1700

Data Index: 3819165 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4423. Min Act: -0.1700

Data Index: 220066 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4383. Min Act: -0.1700

Data Index: 8698356 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4463. Min Act: -0.1700

Data Index: 6269809 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4459. Min Act: -0.1700

Data Index: 8311101 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4115. Min Act: -0.1700

Data Index: 8061655 (Open Web Text)

Max Activating Token Index: 387

Text #17

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4299. Min Act: -0.1700

Data Index: 4956332 (Open Web Text)

Max Activating Token Index: 932

Text #18

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4122. Min Act: -0.1700

Data Index: 838924 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 4.7328. Min Range: -4.7328

Max Act: 4.4294. Min Act: -0.1700

Data Index: 6310226 (Open Web Text)

Max Activating Token Index: 107