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

Dataset: Open Web Text

Neuron 1072 in Layer 2

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: 1.7940. Min Range: -1.7940

Max Act: 1.7940. Min Act: -0.1700

Data Index: 5047424 (Open Web Text)

Max Activating Token Index: 194

Text #1

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7434. Min Act: -0.1700

Data Index: 5987399 (Open Web Text)

Max Activating Token Index: 921

Text #2

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7226. Min Act: -0.1700

Data Index: 2606367 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7279. Min Act: -0.1700

Data Index: 7581215 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7135. Min Act: -0.1700

Data Index: 3004622 (Open Web Text)

Max Activating Token Index: 183

Text #5

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7239. Min Act: -0.1700

Data Index: 2868271 (Open Web Text)

Max Activating Token Index: 214

Text #6

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7221. Min Act: -0.1700

Data Index: 949990 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7021. Min Act: -0.1700

Data Index: 7581222 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7015. Min Act: -0.1700

Data Index: 2258397 (Open Web Text)

Max Activating Token Index: 558

Text #9

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6923. Min Act: -0.1700

Data Index: 8255523 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6776. Min Act: -0.1700

Data Index: 951269 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6936. Min Act: -0.1700

Data Index: 3651360 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6924. Min Act: -0.1700

Data Index: 7288367 (Open Web Text)

Max Activating Token Index: 67

Text #13

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6807. Min Act: -0.1700

Data Index: 4776802 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6861. Min Act: -0.1700

Data Index: 8515580 (Open Web Text)

Max Activating Token Index: 369

Text #15

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6847. Min Act: -0.1700

Data Index: 3359771 (Open Web Text)

Max Activating Token Index: 342

Text #16

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6831. Min Act: -0.1700

Data Index: 2607547 (Open Web Text)

Max Activating Token Index: 302

Text #17

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6770. Min Act: -0.1700

Data Index: 1578289 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6979. Min Act: -0.1700

Data Index: 8484734 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6777. Min Act: -0.1700

Data Index: 7544109 (Open Web Text)

Max Activating Token Index: 174