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

Dataset: Open Web Text

Neuron 1348 in Layer 1

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: 1.8558. Min Range: -1.8558

Max Act: 1.8558. Min Act: -0.1700

Data Index: 2578261 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8409. Min Act: -0.1700

Data Index: 4834148 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8287. Min Act: -0.1700

Data Index: 3981984 (Open Web Text)

Max Activating Token Index: 865

Text #3

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8190. Min Act: -0.1700

Data Index: 8342505 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8272. Min Act: -0.1700

Data Index: 8403096 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8163. Min Act: -0.1700

Data Index: 5545434 (Open Web Text)

Max Activating Token Index: 303

Text #6

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8097. Min Act: -0.1700

Data Index: 5764768 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8156. Min Act: -0.1700

Data Index: 1011775 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7999. Min Act: -0.1700

Data Index: 6818625 (Open Web Text)

Max Activating Token Index: 537

Text #9

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8001. Min Act: -0.1700

Data Index: 5303479 (Open Web Text)

Max Activating Token Index: 724

Text #10

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.8006. Min Act: -0.1700

Data Index: 3723871 (Open Web Text)

Max Activating Token Index: 642

Text #11

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7931. Min Act: -0.1700

Data Index: 7155202 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7992. Min Act: -0.1700

Data Index: 6640652 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7998. Min Act: -0.1700

Data Index: 7613585 (Open Web Text)

Max Activating Token Index: 405

Text #14

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7937. Min Act: -0.1700

Data Index: 594416 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7885. Min Act: -0.1700

Data Index: 7855767 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7760. Min Act: -0.1700

Data Index: 5780594 (Open Web Text)

Max Activating Token Index: 793

Text #17

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7933. Min Act: -0.1700

Data Index: 3681187 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7789. Min Act: -0.1700

Data Index: 699397 (Open Web Text)

Max Activating Token Index: 412

Text #19

Max Range: 1.8558. Min Range: -1.8558

Max Act: 1.7733. Min Act: -0.1700

Data Index: 7014288 (Open Web Text)

Max Activating Token Index: 147