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

Dataset: Open Web Text

Neuron 2385 in Layer 3

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: 3.8441. Min Range: -3.8441

Max Act: 3.8441. Min Act: -0.1700

Data Index: 7576370 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7938. Min Act: -0.1700

Data Index: 2045203 (Open Web Text)

Max Activating Token Index: 169

Text #2

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7844. Min Act: -0.1700

Data Index: 8319893 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7203. Min Act: -0.1700

Data Index: 4103690 (Open Web Text)

Max Activating Token Index: 992

Text #4

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7258. Min Act: -0.1700

Data Index: 2771411 (Open Web Text)

Max Activating Token Index: 186

Text #5

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7283. Min Act: -0.1700

Data Index: 5383502 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6691. Min Act: -0.1700

Data Index: 2458065 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6943. Min Act: -0.1700

Data Index: 8556432 (Open Web Text)

Max Activating Token Index: 366

Text #8

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6767. Min Act: -0.1700

Data Index: 6374848 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7042. Min Act: -0.1700

Data Index: 5741780 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7048. Min Act: -0.1700

Data Index: 5135439 (Open Web Text)

Max Activating Token Index: 93

Text #11

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6621. Min Act: -0.1700

Data Index: 790016 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.5825. Min Act: -0.1700

Data Index: 6022946 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.7010. Min Act: -0.1700

Data Index: 8306289 (Open Web Text)

Max Activating Token Index: 868

Text #14

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1346761 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6967. Min Act: -0.1700

Data Index: 2574243 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6523. Min Act: -0.1700

Data Index: 5613584 (Open Web Text)

Max Activating Token Index: 470

Text #17

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6594. Min Act: -0.1700

Data Index: 558871 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.6153. Min Act: -0.1700

Data Index: 1561229 (Open Web Text)

Max Activating Token Index: 584

Text #19

Max Range: 3.8441. Min Range: -3.8441

Max Act: 3.5579. Min Act: -0.1700

Data Index: 4654997 (Open Web Text)

Max Activating Token Index: 326