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

Dataset: Open Web Text

Neuron 2990 in Layer 2

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: 1.8787. Min Range: -1.8787

Max Act: 1.8787. Min Act: -0.1700

Data Index: 2239580 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8419. Min Act: -0.1700

Data Index: 6058878 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8233. Min Act: -0.1700

Data Index: 7210119 (Open Web Text)

Max Activating Token Index: 773

Text #3

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8173. Min Act: -0.1700

Data Index: 3755889 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8187. Min Act: -0.1700

Data Index: 3264200 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8077. Min Act: -0.1700

Data Index: 2048065 (Open Web Text)

Max Activating Token Index: 969

Text #6

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8087. Min Act: -0.1700

Data Index: 5174331 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8201. Min Act: -0.1700

Data Index: 2988492 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8140. Min Act: -0.1700

Data Index: 5489749 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8166. Min Act: -0.1700

Data Index: 2008200 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8051. Min Act: -0.1700

Data Index: 6590992 (Open Web Text)

Max Activating Token Index: 136

Text #11

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8196. Min Act: -0.1700

Data Index: 1723655 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8060. Min Act: -0.1700

Data Index: 5576462 (Open Web Text)

Max Activating Token Index: 434

Text #13

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.8007. Min Act: -0.1700

Data Index: 8042166 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.7900. Min Act: -0.1700

Data Index: 5676342 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.7946. Min Act: -0.1700

Data Index: 4412796 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.7931. Min Act: -0.1700

Data Index: 8432028 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.7909. Min Act: -0.1700

Data Index: 2823596 (Open Web Text)

Max Activating Token Index: 599

Text #18

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.7875. Min Act: -0.1700

Data Index: 6798968 (Open Web Text)

Max Activating Token Index: 419

Text #19

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.7962. Min Act: -0.1700

Data Index: 1867285 (Open Web Text)

Max Activating Token Index: 103