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

Dataset: Open Web Text

Neuron 2740 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: 3.0340. Min Range: -3.0340

Max Act: 3.0340. Min Act: -0.1700

Data Index: 7220135 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.9545. Min Act: -0.1700

Data Index: 6714392 (Open Web Text)

Max Activating Token Index: 773

Text #2

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8965. Min Act: -0.1700

Data Index: 159478 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8931. Min Act: -0.1700

Data Index: 8394484 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8595. Min Act: -0.1700

Data Index: 2868333 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8595. Min Act: -0.1700

Data Index: 72605 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8263. Min Act: -0.1700

Data Index: 7131740 (Open Web Text)

Max Activating Token Index: 76

Text #7

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8399. Min Act: -0.1700

Data Index: 3540152 (Open Web Text)

Max Activating Token Index: 693

Text #8

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8110. Min Act: -0.1700

Data Index: 3142130 (Open Web Text)

Max Activating Token Index: 610

Text #9

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7911. Min Act: -0.1700

Data Index: 3504128 (Open Web Text)

Max Activating Token Index: 362

Text #10

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8033. Min Act: -0.1700

Data Index: 7847185 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7890. Min Act: -0.1700

Data Index: 4434592 (Open Web Text)

Max Activating Token Index: 171

Text #12

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8012. Min Act: -0.1700

Data Index: 7571986 (Open Web Text)

Max Activating Token Index: 203

Text #13

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8265. Min Act: -0.1700

Data Index: 6475158 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7701. Min Act: -0.1700

Data Index: 765540 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7747. Min Act: -0.1700

Data Index: 3094054 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7772. Min Act: -0.1700

Data Index: 3661351 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7201. Min Act: -0.1700

Data Index: 4281318 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7992. Min Act: -0.1700

Data Index: 7723652 (Open Web Text)

Max Activating Token Index: 668

Text #19

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7743. Min Act: -0.1700

Data Index: 2288794 (Open Web Text)

Max Activating Token Index: 1015