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

Dataset: Open Web Text

Neuron 1525 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: 5.1183. Min Range: -5.1183

Max Act: 5.1183. Min Act: -0.1700

Data Index: 5985094 (Open Web Text)

Max Activating Token Index: 95

Text #1

Max Range: 5.1183. Min Range: -5.1183

Max Act: 5.0794. Min Act: -0.1700

Data Index: 6779046 (Open Web Text)

Max Activating Token Index: 238

Text #2

Max Range: 5.1183. Min Range: -5.1183

Max Act: 5.0602. Min Act: -0.1700

Data Index: 6127972 (Open Web Text)

Max Activating Token Index: 919

Text #3

Max Range: 5.1183. Min Range: -5.1183

Max Act: 5.0354. Min Act: -0.1700

Data Index: 968093 (Open Web Text)

Max Activating Token Index: 117

Text #4

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.9765. Min Act: -0.1700

Data Index: 767087 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.9389. Min Act: -0.1700

Data Index: 7421017 (Open Web Text)

Max Activating Token Index: 281

Text #6

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.9470. Min Act: -0.1700

Data Index: 5501575 (Open Web Text)

Max Activating Token Index: 194

Text #7

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.9624. Min Act: -0.1700

Data Index: 7790664 (Open Web Text)

Max Activating Token Index: 583

Text #8

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8266. Min Act: -0.1700

Data Index: 5446526 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.9240. Min Act: -0.1700

Data Index: 6441730 (Open Web Text)

Max Activating Token Index: 55

Text #10

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.9044. Min Act: -0.1700

Data Index: 1926565 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8718. Min Act: -0.1700

Data Index: 597559 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8909. Min Act: -0.1700

Data Index: 1725432 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8977. Min Act: -0.1700

Data Index: 3707579 (Open Web Text)

Max Activating Token Index: 595

Text #14

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8229. Min Act: -0.1700

Data Index: 775718 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8547. Min Act: -0.1700

Data Index: 965636 (Open Web Text)

Max Activating Token Index: 190

Text #16

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7330. Min Act: -0.1700

Data Index: 1558610 (Open Web Text)

Max Activating Token Index: 230

Text #17

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7995. Min Act: -0.1700

Data Index: 1840705 (Open Web Text)

Max Activating Token Index: 59

Text #18

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7610. Min Act: -0.1700

Data Index: 5202448 (Open Web Text)

Max Activating Token Index: 708

Text #19

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7523. Min Act: -0.1700

Data Index: 75211 (Open Web Text)

Max Activating Token Index: 364