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

Dataset: Open Web Text

Neuron 604 in Layer 4

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: 5.6458. Min Range: -5.6458

Max Act: 5.6458. Min Act: -0.1700

Data Index: 3149200 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.6289. Min Act: -0.1700

Data Index: 6357048 (Open Web Text)

Max Activating Token Index: 365

Text #2

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.6112. Min Act: -0.1700

Data Index: 2896845 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5918. Min Act: -0.1700

Data Index: 8779397 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5774. Min Act: -0.1700

Data Index: 1560167 (Open Web Text)

Max Activating Token Index: 210

Text #5

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.6155. Min Act: -0.1700

Data Index: 5552108 (Open Web Text)

Max Activating Token Index: 575

Text #6

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.6117. Min Act: -0.1700

Data Index: 1442535 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5862. Min Act: -0.1700

Data Index: 3351623 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.6006. Min Act: -0.1700

Data Index: 2004326 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5529. Min Act: -0.1700

Data Index: 3679627 (Open Web Text)

Max Activating Token Index: 486

Text #10

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5835. Min Act: -0.1700

Data Index: 7220346 (Open Web Text)

Max Activating Token Index: 549

Text #11

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5735. Min Act: -0.1700

Data Index: 7595047 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5045. Min Act: -0.1700

Data Index: 2481161 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5923. Min Act: -0.1700

Data Index: 368722 (Open Web Text)

Max Activating Token Index: 425

Text #14

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5890. Min Act: -0.1700

Data Index: 2143621 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.4909. Min Act: -0.1700

Data Index: 3968416 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5692. Min Act: -0.1700

Data Index: 1076054 (Open Web Text)

Max Activating Token Index: 880

Text #17

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5275. Min Act: -0.1700

Data Index: 5868652 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5217. Min Act: -0.1700

Data Index: 7553171 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 5.6458. Min Range: -5.6458

Max Act: 5.5280. Min Act: -0.1700

Data Index: 1003239 (Open Web Text)

Max Activating Token Index: 176