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

Dataset: Open Web Text

Neuron 2480 in Layer 4

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: 4.2493. Min Range: -4.2493

Max Act: 4.1460. Min Act: -0.1700

Data Index: 4628033 (Open Web Text)

Max Activating Token Index: 298

Text #1

Max Range: 4.2493. Min Range: -4.2493

Max Act: 4.2493. Min Act: -0.1700

Data Index: 7166894 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 4.2493. Min Range: -4.2493

Max Act: 4.1327. Min Act: -0.1700

Data Index: 567144 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 4.2493. Min Range: -4.2493

Max Act: 4.0523. Min Act: -0.1700

Data Index: 5516921 (Open Web Text)

Max Activating Token Index: 998

Text #4

Max Range: 4.2493. Min Range: -4.2493

Max Act: 4.0134. Min Act: -0.1700

Data Index: 8435397 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9050. Min Act: -0.1700

Data Index: 8327035 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9554. Min Act: -0.1700

Data Index: 6166401 (Open Web Text)

Max Activating Token Index: 355

Text #7

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9009. Min Act: -0.1700

Data Index: 4692349 (Open Web Text)

Max Activating Token Index: 142

Text #8

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9877. Min Act: -0.1700

Data Index: 6267037 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9913. Min Act: -0.1700

Data Index: 6438709 (Open Web Text)

Max Activating Token Index: 406

Text #10

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9855. Min Act: -0.1700

Data Index: 2507586 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9298. Min Act: -0.1700

Data Index: 770037 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9574. Min Act: -0.1700

Data Index: 553453 (Open Web Text)

Max Activating Token Index: 32

Text #13

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9714. Min Act: -0.1700

Data Index: 669064 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9095. Min Act: -0.1700

Data Index: 3106483 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9058. Min Act: -0.1700

Data Index: 5524624 (Open Web Text)

Max Activating Token Index: 252

Text #16

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9107. Min Act: -0.1700

Data Index: 547523 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 4.2493. Min Range: -4.2493

Max Act: 4.0400. Min Act: -0.1700

Data Index: 3217825 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.9744. Min Act: -0.1700

Data Index: 3599327 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 4.2493. Min Range: -4.2493

Max Act: 3.8956. Min Act: -0.1700

Data Index: 1287296 (Open Web Text)

Max Activating Token Index: 895