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

Dataset: Open Web Text

Neuron 1800 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: 3.9243. Min Range: -3.9243

Max Act: 3.9243. Min Act: -0.1700

Data Index: 1669077 (Open Web Text)

Max Activating Token Index: 321

Text #1

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.7898. Min Act: -0.1700

Data Index: 6856244 (Open Web Text)

Max Activating Token Index: 311

Text #2

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.8044. Min Act: -0.1700

Data Index: 7304299 (Open Web Text)

Max Activating Token Index: 783

Text #3

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.7982. Min Act: -0.1700

Data Index: 4423034 (Open Web Text)

Max Activating Token Index: 278

Text #4

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.8102. Min Act: -0.1700

Data Index: 1279309 (Open Web Text)

Max Activating Token Index: 36

Text #5

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6984. Min Act: -0.1700

Data Index: 2131480 (Open Web Text)

Max Activating Token Index: 186

Text #6

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.7082. Min Act: -0.1700

Data Index: 3568560 (Open Web Text)

Max Activating Token Index: 963

Text #7

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.7030. Min Act: -0.1700

Data Index: 2296700 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6979. Min Act: -0.1700

Data Index: 7469869 (Open Web Text)

Max Activating Token Index: 604

Text #9

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6761. Min Act: -0.1700

Data Index: 2063827 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6460. Min Act: -0.1700

Data Index: 7469867 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6794. Min Act: -0.1700

Data Index: 2288471 (Open Web Text)

Max Activating Token Index: 263

Text #12

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6580. Min Act: -0.1700

Data Index: 2774651 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6203. Min Act: -0.1700

Data Index: 7106542 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6524. Min Act: -0.1700

Data Index: 3217264 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6048. Min Act: -0.1700

Data Index: 8815707 (Open Web Text)

Max Activating Token Index: 533

Text #16

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6132. Min Act: -0.1700

Data Index: 4331230 (Open Web Text)

Max Activating Token Index: 774

Text #17

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.6301. Min Act: -0.1700

Data Index: 4155983 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.5681. Min Act: -0.1700

Data Index: 6220840 (Open Web Text)

Max Activating Token Index: 41

Text #19

Max Range: 3.9243. Min Range: -3.9243

Max Act: 3.5917. Min Act: -0.1700

Data Index: 3708107 (Open Web Text)

Max Activating Token Index: 686