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

Dataset: Open Web Text

Neuron 2821 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: 3.7768. Min Range: -3.7768

Max Act: 3.7768. Min Act: -0.1700

Data Index: 1060850 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.7481. Min Act: -0.1700

Data Index: 6805429 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.6923. Min Act: -0.1700

Data Index: 8713430 (Open Web Text)

Max Activating Token Index: 297

Text #3

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.7112. Min Act: -0.1700

Data Index: 4567755 (Open Web Text)

Max Activating Token Index: 133

Text #4

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.7143. Min Act: -0.1700

Data Index: 3694999 (Open Web Text)

Max Activating Token Index: 643

Text #5

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.6817. Min Act: -0.1700

Data Index: 3745489 (Open Web Text)

Max Activating Token Index: 175

Text #6

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5749. Min Act: -0.1700

Data Index: 3479518 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5926. Min Act: -0.1700

Data Index: 2852430 (Open Web Text)

Max Activating Token Index: 264

Text #8

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.6061. Min Act: -0.1700

Data Index: 5182524 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.6113. Min Act: -0.1700

Data Index: 1116428 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5884. Min Act: -0.1700

Data Index: 4753727 (Open Web Text)

Max Activating Token Index: 282

Text #11

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5644. Min Act: -0.1700

Data Index: 7513918 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5713. Min Act: -0.1700

Data Index: 7678410 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5429. Min Act: -0.1700

Data Index: 3306988 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5399. Min Act: -0.1700

Data Index: 680914 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5481. Min Act: -0.1700

Data Index: 2855261 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5164. Min Act: -0.1700

Data Index: 54265 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5333. Min Act: -0.1700

Data Index: 4697924 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5223. Min Act: -0.1700

Data Index: 3256499 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 3.7768. Min Range: -3.7768

Max Act: 3.5088. Min Act: -0.1700

Data Index: 5560227 (Open Web Text)

Max Activating Token Index: 816