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

Dataset: Open Web Text

Neuron 750 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: 4.0804. Min Range: -4.0804

Max Act: 4.0683. Min Act: -0.1700

Data Index: 1030156 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.0804. Min Range: -4.0804

Max Act: 4.0804. Min Act: -0.1700

Data Index: 5810992 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.0804. Min Range: -4.0804

Max Act: 4.0263. Min Act: -0.1700

Data Index: 8029462 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.0804. Min Range: -4.0804

Max Act: 4.0349. Min Act: -0.1700

Data Index: 3510271 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0804. Min Range: -4.0804

Max Act: 4.0241. Min Act: -0.1700

Data Index: 6474014 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.0804. Min Range: -4.0804

Max Act: 4.0007. Min Act: -0.1700

Data Index: 3353721 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9744. Min Act: -0.1700

Data Index: 5847291 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9446. Min Act: -0.1700

Data Index: 1550811 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9388. Min Act: -0.1700

Data Index: 8704446 (Open Web Text)

Max Activating Token Index: 795

Text #9

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9537. Min Act: -0.1700

Data Index: 2781699 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9540. Min Act: -0.1700

Data Index: 3448631 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9534. Min Act: -0.1700

Data Index: 2984131 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9408. Min Act: -0.1700

Data Index: 3612970 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9445. Min Act: -0.1700

Data Index: 1127497 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9120. Min Act: -0.1700

Data Index: 5279038 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9076. Min Act: -0.1700

Data Index: 4634967 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9316. Min Act: -0.1700

Data Index: 3934472 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9045. Min Act: -0.1700

Data Index: 533042 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9151. Min Act: -0.1700

Data Index: 2274199 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 4.0804. Min Range: -4.0804

Max Act: 3.9270. Min Act: -0.1700

Data Index: 261365 (Open Web Text)

Max Activating Token Index: 681