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

Dataset: Open Web Text

Neuron 502 in Layer 6

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: 4.0255. Min Range: -4.0255

Max Act: 4.0255. Min Act: -0.1700

Data Index: 319036 (Open Web Text)

Max Activating Token Index: 795

Text #1

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.9206. Min Act: -0.1700

Data Index: 2010835 (Open Web Text)

Max Activating Token Index: 203

Text #2

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.8698. Min Act: -0.1700

Data Index: 1752825 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.8613. Min Act: -0.1700

Data Index: 2501629 (Open Web Text)

Max Activating Token Index: 345

Text #4

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.8580. Min Act: -0.1700

Data Index: 4691238 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.8291. Min Act: -0.1700

Data Index: 5475004 (Open Web Text)

Max Activating Token Index: 189

Text #6

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.8217. Min Act: -0.1700

Data Index: 4939627 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7731. Min Act: -0.1700

Data Index: 7100222 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7704. Min Act: -0.1700

Data Index: 3471274 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7653. Min Act: -0.1700

Data Index: 6289371 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7580. Min Act: -0.1700

Data Index: 8562656 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7545. Min Act: -0.1700

Data Index: 2843188 (Open Web Text)

Max Activating Token Index: 205

Text #12

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7653. Min Act: -0.1700

Data Index: 8358966 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7454. Min Act: -0.1700

Data Index: 5682627 (Open Web Text)

Max Activating Token Index: 1013

Text #14

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7183. Min Act: -0.1700

Data Index: 6112619 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7037. Min Act: -0.1700

Data Index: 7424690 (Open Web Text)

Max Activating Token Index: 738

Text #16

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7094. Min Act: -0.1700

Data Index: 8111985 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.6894. Min Act: -0.1700

Data Index: 5433560 (Open Web Text)

Max Activating Token Index: 826

Text #18

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.6971. Min Act: -0.1700

Data Index: 2498185 (Open Web Text)

Max Activating Token Index: 232

Text #19

Max Range: 4.0255. Min Range: -4.0255

Max Act: 3.7021. Min Act: -0.1700

Data Index: 2143041 (Open Web Text)

Max Activating Token Index: 581