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

Dataset: Open Web Text

Neuron 1051 in Layer 4

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: 3.6904. Min Range: -3.6904

Max Act: 3.6904. Min Act: -0.1700

Data Index: 6515408 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6573. Min Act: -0.1700

Data Index: 1974995 (Open Web Text)

Max Activating Token Index: 217

Text #2

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6334. Min Act: -0.1700

Data Index: 2715880 (Open Web Text)

Max Activating Token Index: 182

Text #3

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6157. Min Act: -0.1700

Data Index: 2054565 (Open Web Text)

Max Activating Token Index: 59

Text #4

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6018. Min Act: -0.1700

Data Index: 3171908 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6204. Min Act: -0.1700

Data Index: 7263215 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6144. Min Act: -0.1700

Data Index: 6607245 (Open Web Text)

Max Activating Token Index: 527

Text #7

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6048. Min Act: -0.1700

Data Index: 8132113 (Open Web Text)

Max Activating Token Index: 86

Text #8

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6028. Min Act: -0.1700

Data Index: 2807507 (Open Web Text)

Max Activating Token Index: 865

Text #9

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6093. Min Act: -0.1700

Data Index: 2288486 (Open Web Text)

Max Activating Token Index: 904

Text #10

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6036. Min Act: -0.1700

Data Index: 4357436 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.5433. Min Act: -0.1700

Data Index: 4947626 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.5964. Min Act: -0.1700

Data Index: 3659141 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6028. Min Act: -0.1700

Data Index: 1760463 (Open Web Text)

Max Activating Token Index: 733

Text #14

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.5693. Min Act: -0.1700

Data Index: 2097804 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.5663. Min Act: -0.1700

Data Index: 7495590 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.6035. Min Act: -0.1700

Data Index: 3883837 (Open Web Text)

Max Activating Token Index: 534

Text #17

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.5452. Min Act: -0.1700

Data Index: 2935131 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.5293. Min Act: -0.1700

Data Index: 5281958 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 3.6904. Min Range: -3.6904

Max Act: 3.4928. Min Act: -0.1700

Data Index: 1926464 (Open Web Text)

Max Activating Token Index: 613