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

Dataset: Open Web Text

Neuron 495 in Layer 5

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: 3.8333. Min Range: -3.8333

Max Act: 3.8333. Min Act: -0.1700

Data Index: 6963719 (Open Web Text)

Max Activating Token Index: 476

Text #1

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5359. Min Act: -0.1700

Data Index: 517277 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.6258. Min Act: -0.1700

Data Index: 8225919 (Open Web Text)

Max Activating Token Index: 474

Text #3

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5508. Min Act: -0.1700

Data Index: 4707581 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5885. Min Act: -0.1700

Data Index: 3914280 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5917. Min Act: -0.1700

Data Index: 5472078 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5644. Min Act: -0.1700

Data Index: 431175 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5249. Min Act: -0.1700

Data Index: 7258903 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.4946. Min Act: -0.1700

Data Index: 6018428 (Open Web Text)

Max Activating Token Index: 173

Text #9

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5088. Min Act: -0.1700

Data Index: 4477269 (Open Web Text)

Max Activating Token Index: 331

Text #10

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5682. Min Act: -0.1700

Data Index: 1274309 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5171. Min Act: -0.1700

Data Index: 579585 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.4455. Min Act: -0.1700

Data Index: 7239905 (Open Web Text)

Max Activating Token Index: 200

Text #13

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5011. Min Act: -0.1700

Data Index: 6702893 (Open Web Text)

Max Activating Token Index: 568

Text #14

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.5005. Min Act: -0.1700

Data Index: 356862 (Open Web Text)

Max Activating Token Index: 210

Text #15

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.4706. Min Act: -0.1700

Data Index: 511695 (Open Web Text)

Max Activating Token Index: 468

Text #16

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.4642. Min Act: -0.1700

Data Index: 8147635 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.4524. Min Act: -0.1700

Data Index: 7889324 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.4564. Min Act: -0.1700

Data Index: 7829364 (Open Web Text)

Max Activating Token Index: 539

Text #19

Max Range: 3.8333. Min Range: -3.8333

Max Act: 3.4371. Min Act: -0.1700

Data Index: 5927326 (Open Web Text)

Max Activating Token Index: 208