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

Dataset: Open Web Text

Neuron 1629 in Layer 0

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: 1.3728. Min Range: -1.3728

Max Act: 1.3668. Min Act: -0.1261

Data Index: 6934506 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3728. Min Act: -0.1099

Data Index: 310478 (Open Web Text)

Max Activating Token Index: 985

Text #2

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3506. Min Act: -0.0750

Data Index: 7475767 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3430. Min Act: -0.1357

Data Index: 690519 (Open Web Text)

Max Activating Token Index: 62

Text #4

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3370. Min Act: -0.1187

Data Index: 5308485 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3231. Min Act: -0.0750

Data Index: 1076100 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3182. Min Act: -0.0803

Data Index: 3157872 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3177. Min Act: -0.1172

Data Index: 2523579 (Open Web Text)

Max Activating Token Index: 928

Text #8

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3101. Min Act: -0.0763

Data Index: 310475 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3004. Min Act: -0.1099

Data Index: 2845823 (Open Web Text)

Max Activating Token Index: 874

Text #10

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3076. Min Act: -0.1187

Data Index: 6728905 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3077. Min Act: -0.0750

Data Index: 3720785 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3088. Min Act: -0.0966

Data Index: 3867763 (Open Web Text)

Max Activating Token Index: 200

Text #13

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3139. Min Act: -0.0788

Data Index: 7475778 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3010. Min Act: -0.0872

Data Index: 4223195 (Open Web Text)

Max Activating Token Index: 941

Text #15

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2997. Min Act: -0.1163

Data Index: 3867761 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2974. Min Act: -0.1238

Data Index: 3867762 (Open Web Text)

Max Activating Token Index: 964

Text #17

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2936. Min Act: -0.0750

Data Index: 3390084 (Open Web Text)

Max Activating Token Index: 779

Text #18

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2868. Min Act: -0.1348

Data Index: 4355793 (Open Web Text)

Max Activating Token Index: 966

Text #19

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2848. Min Act: -0.0750

Data Index: 5719185 (Open Web Text)

Max Activating Token Index: 915