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

Dataset: Open Web Text

Neuron 2855 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: 3.4927. Min Range: -3.4927

Max Act: 3.4927. Min Act: -0.1700

Data Index: 6985870 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.4473. Min Act: -0.1700

Data Index: 5980234 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3516. Min Act: -0.1700

Data Index: 2814575 (Open Web Text)

Max Activating Token Index: 258

Text #3

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3797. Min Act: -0.1700

Data Index: 5341126 (Open Web Text)

Max Activating Token Index: 937

Text #4

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3426. Min Act: -0.1700

Data Index: 2526042 (Open Web Text)

Max Activating Token Index: 292

Text #5

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3397. Min Act: -0.1700

Data Index: 33565 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3293. Min Act: -0.1700

Data Index: 6631059 (Open Web Text)

Max Activating Token Index: 587

Text #7

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3134. Min Act: -0.1700

Data Index: 7846933 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3152. Min Act: -0.1700

Data Index: 1062376 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3306. Min Act: -0.1700

Data Index: 48267 (Open Web Text)

Max Activating Token Index: 289

Text #10

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3024. Min Act: -0.1700

Data Index: 1900712 (Open Web Text)

Max Activating Token Index: 873

Text #11

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3237. Min Act: -0.1700

Data Index: 6594999 (Open Web Text)

Max Activating Token Index: 935

Text #12

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.3402. Min Act: -0.1700

Data Index: 5868088 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2981. Min Act: -0.1700

Data Index: 6741214 (Open Web Text)

Max Activating Token Index: 249

Text #14

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2934. Min Act: -0.1700

Data Index: 4934550 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2787. Min Act: -0.1700

Data Index: 5200592 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2923. Min Act: -0.1700

Data Index: 3944063 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2769. Min Act: -0.1700

Data Index: 7125728 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2627. Min Act: -0.1700

Data Index: 2877893 (Open Web Text)

Max Activating Token Index: 708

Text #19

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2576. Min Act: -0.1700

Data Index: 4814202 (Open Web Text)

Max Activating Token Index: 316