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

Dataset: Open Web Text

Neuron 1485 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: 3.9467. Min Range: -3.9467

Max Act: 3.9467. Min Act: -0.1700

Data Index: 4077941 (Open Web Text)

Max Activating Token Index: 288

Text #1

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8947. Min Act: -0.1700

Data Index: 3810069 (Open Web Text)

Max Activating Token Index: 769

Text #2

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8897. Min Act: -0.1700

Data Index: 7904379 (Open Web Text)

Max Activating Token Index: 601

Text #3

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8878. Min Act: -0.1700

Data Index: 1183590 (Open Web Text)

Max Activating Token Index: 190

Text #4

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8595. Min Act: -0.1700

Data Index: 6196857 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8671. Min Act: -0.1700

Data Index: 2503504 (Open Web Text)

Max Activating Token Index: 592

Text #6

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8552. Min Act: -0.1700

Data Index: 5292664 (Open Web Text)

Max Activating Token Index: 571

Text #7

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8125. Min Act: -0.1700

Data Index: 2073476 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8126. Min Act: -0.1700

Data Index: 6267758 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8103. Min Act: -0.1700

Data Index: 5488205 (Open Web Text)

Max Activating Token Index: 108

Text #10

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8473. Min Act: -0.1700

Data Index: 7239024 (Open Web Text)

Max Activating Token Index: 361

Text #11

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8304. Min Act: -0.1700

Data Index: 6621004 (Open Web Text)

Max Activating Token Index: 999

Text #12

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7832. Min Act: -0.1700

Data Index: 2658497 (Open Web Text)

Max Activating Token Index: 652

Text #13

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8085. Min Act: -0.1700

Data Index: 6624308 (Open Web Text)

Max Activating Token Index: 733

Text #14

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7854. Min Act: -0.1700

Data Index: 139234 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7726. Min Act: -0.1700

Data Index: 3512630 (Open Web Text)

Max Activating Token Index: 167

Text #16

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7610. Min Act: -0.1700

Data Index: 5083950 (Open Web Text)

Max Activating Token Index: 637

Text #17

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7799. Min Act: -0.1700

Data Index: 2868046 (Open Web Text)

Max Activating Token Index: 521

Text #18

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1089639 (Open Web Text)

Max Activating Token Index: 712

Text #19

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7655. Min Act: -0.1700

Data Index: 799701 (Open Web Text)

Max Activating Token Index: 801