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

Dataset: Open Web Text

Neuron 2276 in Layer 0

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: 3.6514. Min Range: -3.6514

Max Act: 3.6200. Min Act: -0.1700

Data Index: 3806678 (Open Web Text)

Max Activating Token Index: 883

Text #1

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6345. Min Act: -0.1700

Data Index: 7133757 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6514. Min Act: -0.1700

Data Index: 4070767 (Open Web Text)

Max Activating Token Index: 793

Text #3

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5990. Min Act: -0.1700

Data Index: 2959991 (Open Web Text)

Max Activating Token Index: 727

Text #4

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1390617 (Open Web Text)

Max Activating Token Index: 796

Text #5

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6013. Min Act: -0.1700

Data Index: 1805568 (Open Web Text)

Max Activating Token Index: 974

Text #6

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5860. Min Act: -0.1700

Data Index: 879306 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6039. Min Act: -0.1700

Data Index: 4678895 (Open Web Text)

Max Activating Token Index: 288

Text #8

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5975. Min Act: -0.1700

Data Index: 2718616 (Open Web Text)

Max Activating Token Index: 960

Text #9

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6075. Min Act: -0.1700

Data Index: 2372284 (Open Web Text)

Max Activating Token Index: 918

Text #10

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5811. Min Act: -0.1700

Data Index: 2317837 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6000. Min Act: -0.1700

Data Index: 3403646 (Open Web Text)

Max Activating Token Index: 667

Text #12

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6087. Min Act: -0.1700

Data Index: 1946022 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5958. Min Act: -0.1700

Data Index: 6752763 (Open Web Text)

Max Activating Token Index: 255

Text #14

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.6097. Min Act: -0.1700

Data Index: 5692201 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5702. Min Act: -0.1700

Data Index: 4559219 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5921. Min Act: -0.1700

Data Index: 4609070 (Open Web Text)

Max Activating Token Index: 732

Text #17

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5413. Min Act: -0.1700

Data Index: 1714569 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5461. Min Act: -0.1700

Data Index: 4880637 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 3.6514. Min Range: -3.6514

Max Act: 3.5487. Min Act: -0.1700

Data Index: 5034982 (Open Web Text)

Max Activating Token Index: 6