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

Dataset: Open Web Text

Neuron 343 in Layer 2

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: 1.8726. Min Range: -1.8726

Max Act: 1.8726. Min Act: -0.1700

Data Index: 1434061 (Open Web Text)

Max Activating Token Index: 551

Text #1

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.8646. Min Act: -0.1700

Data Index: 6919007 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.8349. Min Act: -0.1700

Data Index: 7009502 (Open Web Text)

Max Activating Token Index: 712

Text #3

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.8441. Min Act: -0.1700

Data Index: 291058 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.8167. Min Act: -0.1700

Data Index: 4675267 (Open Web Text)

Max Activating Token Index: 209

Text #5

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.8214. Min Act: -0.1700

Data Index: 2869767 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.8171. Min Act: -0.1700

Data Index: 2998339 (Open Web Text)

Max Activating Token Index: 452

Text #7

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7994. Min Act: -0.1700

Data Index: 745787 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7942. Min Act: -0.1700

Data Index: 1492634 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7968. Min Act: -0.1700

Data Index: 3346269 (Open Web Text)

Max Activating Token Index: 649

Text #10

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7874. Min Act: -0.1700

Data Index: 2735334 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7901. Min Act: -0.1700

Data Index: 2648558 (Open Web Text)

Max Activating Token Index: 879

Text #12

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7960. Min Act: -0.1700

Data Index: 5005831 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7922. Min Act: -0.1700

Data Index: 4399330 (Open Web Text)

Max Activating Token Index: 450

Text #14

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7766. Min Act: -0.1700

Data Index: 3232344 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7880. Min Act: -0.1700

Data Index: 2558674 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7875. Min Act: -0.1700

Data Index: 659020 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7947. Min Act: -0.1700

Data Index: 8216545 (Open Web Text)

Max Activating Token Index: 457

Text #18

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7795. Min Act: -0.1700

Data Index: 3222992 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 1.8726. Min Range: -1.8726

Max Act: 1.7630. Min Act: -0.1700

Data Index: 4573298 (Open Web Text)

Max Activating Token Index: 954