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

Dataset: Open Web Text

Neuron 1576 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: 6.5450. Min Range: -6.5450

Max Act: 6.5450. Min Act: -0.1700

Data Index: 4465897 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.4424. Min Act: -0.1700

Data Index: 7223349 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.4400. Min Act: -0.1700

Data Index: 1205309 (Open Web Text)

Max Activating Token Index: 259

Text #3

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.4068. Min Act: -0.1700

Data Index: 8696993 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.4269. Min Act: -0.1700

Data Index: 7875549 (Open Web Text)

Max Activating Token Index: 255

Text #5

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.3930. Min Act: -0.1700

Data Index: 912689 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.3819. Min Act: -0.1700

Data Index: 5239070 (Open Web Text)

Max Activating Token Index: 240

Text #7

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.2928. Min Act: -0.1700

Data Index: 5298421 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.3942. Min Act: -0.1700

Data Index: 3895216 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.3223. Min Act: -0.1698

Data Index: 5601136 (Open Web Text)

Max Activating Token Index: 67

Text #10

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.2898. Min Act: -0.1700

Data Index: 4235368 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.2411. Min Act: -0.1700

Data Index: 5692645 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.2539. Min Act: -0.1700

Data Index: 2617217 (Open Web Text)

Max Activating Token Index: 968

Text #13

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.2584. Min Act: -0.1699

Data Index: 2787512 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.2503. Min Act: -0.1700

Data Index: 781305 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.1719. Min Act: -0.1700

Data Index: 7453577 (Open Web Text)

Max Activating Token Index: 164

Text #16

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.2470. Min Act: -0.1700

Data Index: 8213222 (Open Web Text)

Max Activating Token Index: 725

Text #17

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.1874. Min Act: -0.1700

Data Index: 5922923 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.1999. Min Act: -0.1700

Data Index: 3778801 (Open Web Text)

Max Activating Token Index: 922

Text #19

Max Range: 6.5450. Min Range: -6.5450

Max Act: 6.0703. Min Act: -0.1700

Data Index: 7157815 (Open Web Text)

Max Activating Token Index: 539