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

Dataset: Open Web Text

Neuron 118 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: 5.1455. Min Range: -5.1455

Max Act: 5.1455. Min Act: -0.1700

Data Index: 2872121 (Open Web Text)

Max Activating Token Index: 856

Text #1

Max Range: 5.1455. Min Range: -5.1455

Max Act: 5.0503. Min Act: -0.1700

Data Index: 4581023 (Open Web Text)

Max Activating Token Index: 912

Text #2

Max Range: 5.1455. Min Range: -5.1455

Max Act: 5.1103. Min Act: -0.1700

Data Index: 3600007 (Open Web Text)

Max Activating Token Index: 730

Text #3

Max Range: 5.1455. Min Range: -5.1455

Max Act: 5.0598. Min Act: -0.1700

Data Index: 6651516 (Open Web Text)

Max Activating Token Index: 493

Text #4

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9757. Min Act: -0.1700

Data Index: 3243127 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9960. Min Act: -0.1700

Data Index: 2683409 (Open Web Text)

Max Activating Token Index: 699

Text #6

Max Range: 5.1455. Min Range: -5.1455

Max Act: 5.0013. Min Act: -0.1700

Data Index: 7096210 (Open Web Text)

Max Activating Token Index: 644

Text #7

Max Range: 5.1455. Min Range: -5.1455

Max Act: 5.0097. Min Act: -0.1700

Data Index: 3428249 (Open Web Text)

Max Activating Token Index: 843

Text #8

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9643. Min Act: -0.1700

Data Index: 5727401 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9453. Min Act: -0.1700

Data Index: 3459049 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9612. Min Act: -0.1700

Data Index: 3964211 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9442. Min Act: -0.1700

Data Index: 5286904 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9057. Min Act: -0.1700

Data Index: 4089894 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9055. Min Act: -0.1700

Data Index: 4479224 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9013. Min Act: -0.1700

Data Index: 325954 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9092. Min Act: -0.1700

Data Index: 8236038 (Open Web Text)

Max Activating Token Index: 813

Text #16

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9111. Min Act: -0.1700

Data Index: 673499 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9301. Min Act: -0.1700

Data Index: 5523740 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9191. Min Act: -0.1700

Data Index: 4942013 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 5.1455. Min Range: -5.1455

Max Act: 4.9235. Min Act: -0.1700

Data Index: 5175277 (Open Web Text)

Max Activating Token Index: 994