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

Dataset: Open Web Text

Neuron 3011 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: 2.1820. Min Range: -2.1820

Max Act: 2.1820. Min Act: -0.1700

Data Index: 7215366 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1628. Min Act: -0.1700

Data Index: 1951093 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1626. Min Act: -0.1700

Data Index: 6495225 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1626. Min Act: -0.1700

Data Index: 2594520 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1508. Min Act: -0.1700

Data Index: 5523857 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1431. Min Act: -0.1700

Data Index: 8409243 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1250. Min Act: -0.1700

Data Index: 3606627 (Open Web Text)

Max Activating Token Index: 224

Text #7

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1176. Min Act: -0.1700

Data Index: 601583 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1100. Min Act: -0.1700

Data Index: 2719765 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1111. Min Act: -0.1700

Data Index: 3988911 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.1051. Min Act: -0.1700

Data Index: 5300450 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0981. Min Act: -0.1700

Data Index: 1985208 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0924. Min Act: -0.1700

Data Index: 6082419 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0918. Min Act: -0.1700

Data Index: 7818309 (Open Web Text)

Max Activating Token Index: 744

Text #14

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0858. Min Act: -0.1700

Data Index: 6832279 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0730. Min Act: -0.1700

Data Index: 7082032 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0694. Min Act: -0.1700

Data Index: 8511588 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0602. Min Act: -0.1700

Data Index: 9731 (Open Web Text)

Max Activating Token Index: 131

Text #18

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0423. Min Act: -0.1700

Data Index: 7767427 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 2.1820. Min Range: -2.1820

Max Act: 2.0359. Min Act: -0.1700

Data Index: 585634 (Open Web Text)

Max Activating Token Index: 2