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

Dataset: Open Web Text

Neuron 2545 in Layer 5

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: 3.8329. Min Range: -3.8329

Max Act: 3.8329. Min Act: -0.1700

Data Index: 6201269 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.7492. Min Act: -0.1700

Data Index: 4867086 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.7355. Min Act: -0.1700

Data Index: 8664757 (Open Web Text)

Max Activating Token Index: 544

Text #3

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.7015. Min Act: -0.1700

Data Index: 17778 (Open Web Text)

Max Activating Token Index: 936

Text #4

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6446. Min Act: -0.1700

Data Index: 3898368 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6603. Min Act: -0.1700

Data Index: 2201663 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6563. Min Act: -0.1700

Data Index: 7660074 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6442. Min Act: -0.1700

Data Index: 4631840 (Open Web Text)

Max Activating Token Index: 90

Text #8

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6220. Min Act: -0.1700

Data Index: 2133388 (Open Web Text)

Max Activating Token Index: 942

Text #9

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6143. Min Act: -0.1700

Data Index: 2047550 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6209. Min Act: -0.1700

Data Index: 7810573 (Open Web Text)

Max Activating Token Index: 244

Text #11

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6317. Min Act: -0.1700

Data Index: 4685475 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6512. Min Act: -0.1700

Data Index: 4235408 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6418. Min Act: -0.1700

Data Index: 1814822 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6319. Min Act: -0.1700

Data Index: 8260259 (Open Web Text)

Max Activating Token Index: 132

Text #15

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6081. Min Act: -0.1700

Data Index: 7520681 (Open Web Text)

Max Activating Token Index: 948

Text #16

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.5850. Min Act: -0.1700

Data Index: 4790833 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.6023. Min Act: -0.1700

Data Index: 6452400 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.5891. Min Act: -0.1700

Data Index: 851530 (Open Web Text)

Max Activating Token Index: 983

Text #19

Max Range: 3.8329. Min Range: -3.8329

Max Act: 3.5945. Min Act: -0.1700

Data Index: 7843764 (Open Web Text)

Max Activating Token Index: 996