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

Dataset: Open Web Text

Neuron 1603 in Layer 1

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: 1.8148. Min Range: -1.8148

Max Act: 1.8148. Min Act: -0.1700

Data Index: 2205206 (Open Web Text)

Max Activating Token Index: 111

Text #1

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.8005. Min Act: -0.1700

Data Index: 8723012 (Open Web Text)

Max Activating Token Index: 499

Text #2

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7991. Min Act: -0.1699

Data Index: 2205211 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7919. Min Act: -0.1700

Data Index: 2538915 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7790. Min Act: -0.1700

Data Index: 7238212 (Open Web Text)

Max Activating Token Index: 1009

Text #5

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7616. Min Act: -0.1700

Data Index: 8648687 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7576. Min Act: -0.1700

Data Index: 8443523 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7643. Min Act: -0.1700

Data Index: 7971569 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7401. Min Act: -0.1700

Data Index: 1846085 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7400. Min Act: -0.1700

Data Index: 3662954 (Open Web Text)

Max Activating Token Index: 819

Text #10

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7402. Min Act: -0.1700

Data Index: 7371610 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7339. Min Act: -0.1700

Data Index: 6672464 (Open Web Text)

Max Activating Token Index: 566

Text #12

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7290. Min Act: -0.1700

Data Index: 4767103 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7349. Min Act: -0.1700

Data Index: 3180887 (Open Web Text)

Max Activating Token Index: 96

Text #14

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7261. Min Act: -0.1700

Data Index: 3029639 (Open Web Text)

Max Activating Token Index: 873

Text #15

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7353. Min Act: -0.1700

Data Index: 7753768 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7250. Min Act: -0.1700

Data Index: 2556912 (Open Web Text)

Max Activating Token Index: 33

Text #17

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7249. Min Act: -0.1700

Data Index: 3795250 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7241. Min Act: -0.1700

Data Index: 3990597 (Open Web Text)

Max Activating Token Index: 460

Text #19

Max Range: 1.8148. Min Range: -1.8148

Max Act: 1.7122. Min Act: -0.1700

Data Index: 6888947 (Open Web Text)

Max Activating Token Index: 584