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

Dataset: Open Web Text

Neuron 900 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: 3.9626. Min Range: -3.9626

Max Act: 3.9626. Min Act: -0.1700

Data Index: 6953086 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6970. Min Act: -0.1700

Data Index: 2835190 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6580. Min Act: -0.1700

Data Index: 8658683 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.5887. Min Act: -0.1700

Data Index: 8779970 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.5586. Min Act: -0.1700

Data Index: 5089529 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.5329. Min Act: -0.1700

Data Index: 8578713 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.4937. Min Act: -0.1700

Data Index: 8826900 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.4783. Min Act: -0.1700

Data Index: 2878895 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.4902. Min Act: -0.1700

Data Index: 6525383 (Open Web Text)

Max Activating Token Index: 1008

Text #9

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.4605. Min Act: -0.1700

Data Index: 2001685 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.4059. Min Act: -0.1700

Data Index: 502777 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.4153. Min Act: -0.1700

Data Index: 3809484 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.3416. Min Act: -0.1700

Data Index: 7793597 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.3392. Min Act: -0.1700

Data Index: 6965546 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.3003. Min Act: -0.1700

Data Index: 4037361 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.3025. Min Act: -0.1700

Data Index: 4446360 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2672. Min Act: -0.1700

Data Index: 2058821 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2583. Min Act: -0.1700

Data Index: 6726564 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2630. Min Act: -0.1700

Data Index: 4838963 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.2296. Min Act: -0.1700

Data Index: 8366696 (Open Web Text)

Max Activating Token Index: 1023