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

Dataset: Open Web Text

Neuron 2676 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: 4.6335. Min Range: -4.6335

Max Act: 4.6335. Min Act: -0.1700

Data Index: 926602 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4904. Min Act: -0.1700

Data Index: 3346750 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4559. Min Act: -0.1700

Data Index: 4766850 (Open Web Text)

Max Activating Token Index: 627

Text #3

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4455. Min Act: -0.1700

Data Index: 4573026 (Open Web Text)

Max Activating Token Index: 529

Text #4

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4316. Min Act: -0.1700

Data Index: 2952101 (Open Web Text)

Max Activating Token Index: 211

Text #5

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4392. Min Act: -0.1698

Data Index: 8564027 (Open Web Text)

Max Activating Token Index: 370

Text #6

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4597. Min Act: -0.1700

Data Index: 148219 (Open Web Text)

Max Activating Token Index: 322

Text #7

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4370. Min Act: -0.1700

Data Index: 3808756 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4527. Min Act: -0.1700

Data Index: 4538280 (Open Web Text)

Max Activating Token Index: 717

Text #9

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4132. Min Act: -0.1700

Data Index: 4392973 (Open Web Text)

Max Activating Token Index: 733

Text #10

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4388. Min Act: -0.1700

Data Index: 710988 (Open Web Text)

Max Activating Token Index: 943

Text #11

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4505. Min Act: -0.1700

Data Index: 1156666 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3865. Min Act: -0.1700

Data Index: 4164575 (Open Web Text)

Max Activating Token Index: 801

Text #13

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3520. Min Act: -0.1700

Data Index: 8797230 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4125. Min Act: -0.1700

Data Index: 6788418 (Open Web Text)

Max Activating Token Index: 846

Text #15

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3795. Min Act: -0.1700

Data Index: 8172257 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3493. Min Act: -0.1700

Data Index: 2535169 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3939. Min Act: -0.1700

Data Index: 2527260 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3089. Min Act: -0.1700

Data Index: 6034332 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4095. Min Act: -0.1700

Data Index: 2217116 (Open Web Text)

Max Activating Token Index: 380