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

Dataset: Open Web Text

Neuron 2959 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: 2.8852. Min Range: -2.8852

Max Act: 2.8852. Min Act: -0.1700

Data Index: 444587 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.8668. Min Act: -0.1700

Data Index: 1286877 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.8623. Min Act: -0.1700

Data Index: 867746 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.8272. Min Act: -0.1700

Data Index: 4805755 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.7938. Min Act: -0.1700

Data Index: 6218765 (Open Web Text)

Max Activating Token Index: 638

Text #5

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.7981. Min Act: -0.1700

Data Index: 3234223 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.7772. Min Act: -0.1700

Data Index: 86197 (Open Web Text)

Max Activating Token Index: 957

Text #7

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.7346. Min Act: -0.1700

Data Index: 2841001 (Open Web Text)

Max Activating Token Index: 758

Text #8

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6931. Min Act: -0.1700

Data Index: 5233320 (Open Web Text)

Max Activating Token Index: 928

Text #9

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6617. Min Act: -0.1700

Data Index: 6246180 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6577. Min Act: -0.1700

Data Index: 2623414 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6418. Min Act: -0.1700

Data Index: 6353527 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6302. Min Act: -0.1700

Data Index: 8298364 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6178. Min Act: -0.1700

Data Index: 5476557 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6035. Min Act: -0.1700

Data Index: 6420635 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6109. Min Act: -0.1700

Data Index: 6598932 (Open Web Text)

Max Activating Token Index: 119

Text #16

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.6247. Min Act: -0.1700

Data Index: 6968350 (Open Web Text)

Max Activating Token Index: 105

Text #17

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.5965. Min Act: -0.1700

Data Index: 6282751 (Open Web Text)

Max Activating Token Index: 715

Text #18

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.5892. Min Act: -0.1700

Data Index: 5546299 (Open Web Text)

Max Activating Token Index: 919

Text #19

Max Range: 2.8852. Min Range: -2.8852

Max Act: 2.5910. Min Act: -0.1700

Data Index: 6372387 (Open Web Text)

Max Activating Token Index: 128