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

Dataset: Open Web Text

Neuron 3069 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: 4.6259. Min Range: -4.6259

Max Act: 4.6259. Min Act: -0.1700

Data Index: 2794664 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5893. Min Act: -0.1700

Data Index: 6794494 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5870. Min Act: -0.1700

Data Index: 1098352 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5581. Min Act: -0.1700

Data Index: 7701958 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5707. Min Act: -0.1700

Data Index: 5780944 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5720. Min Act: -0.1700

Data Index: 2841498 (Open Web Text)

Max Activating Token Index: 482

Text #6

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5465. Min Act: -0.1700

Data Index: 1611101 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5122. Min Act: -0.1700

Data Index: 1136178 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5301. Min Act: -0.1700

Data Index: 8372507 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5208. Min Act: -0.1700

Data Index: 5870848 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5308. Min Act: -0.1700

Data Index: 1331384 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5511. Min Act: -0.1700

Data Index: 2359225 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5107. Min Act: -0.1700

Data Index: 3980255 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.4906. Min Act: -0.1700

Data Index: 215741 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.4849. Min Act: -0.1700

Data Index: 1388244 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.4933. Min Act: -0.1700

Data Index: 4832466 (Open Web Text)

Max Activating Token Index: 630

Text #16

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.4780. Min Act: -0.1700

Data Index: 3926790 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.4969. Min Act: -0.1700

Data Index: 6396728 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.5106. Min Act: -0.1700

Data Index: 3534868 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.6259. Min Range: -4.6259

Max Act: 4.4734. Min Act: -0.1700

Data Index: 1542581 (Open Web Text)

Max Activating Token Index: 21