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

Dataset: Open Web Text

Neuron 3051 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: 2.9319. Min Range: -2.9319

Max Act: 2.9319. Min Act: -0.1700

Data Index: 2636627 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8678. Min Act: -0.1700

Data Index: 1599342 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8292. Min Act: -0.1700

Data Index: 2457713 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8265. Min Act: -0.1700

Data Index: 3367012 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8296. Min Act: -0.1700

Data Index: 5865270 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8095. Min Act: -0.1700

Data Index: 7220795 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8106. Min Act: -0.1700

Data Index: 3407471 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8039. Min Act: -0.1700

Data Index: 4106123 (Open Web Text)

Max Activating Token Index: 88

Text #8

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8133. Min Act: -0.1700

Data Index: 5771235 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8113. Min Act: -0.1700

Data Index: 1071502 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.8007. Min Act: -0.1700

Data Index: 561603 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7895. Min Act: -0.1700

Data Index: 2063191 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7934. Min Act: -0.1700

Data Index: 7413925 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7849. Min Act: -0.1700

Data Index: 3353557 (Open Web Text)

Max Activating Token Index: 724

Text #14

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7804. Min Act: -0.1700

Data Index: 6420756 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7800. Min Act: -0.1700

Data Index: 7797322 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7699. Min Act: -0.1700

Data Index: 3275051 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7764. Min Act: -0.1700

Data Index: 166010 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7806. Min Act: -0.1700

Data Index: 5520257 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.9319. Min Range: -2.9319

Max Act: 2.7573. Min Act: -0.1700

Data Index: 3259781 (Open Web Text)

Max Activating Token Index: 146