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

Dataset: Open Web Text

Neuron 1002 in Layer 6

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: 6.6907. Min Range: -6.6907

Max Act: 6.6907. Min Act: -0.1700

Data Index: 1856283 (Open Web Text)

Max Activating Token Index: 976

Text #1

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.6450. Min Act: -0.1700

Data Index: 6030718 (Open Web Text)

Max Activating Token Index: 626

Text #2

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.5254. Min Act: -0.1700

Data Index: 3869565 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.4890. Min Act: -0.1700

Data Index: 6896149 (Open Web Text)

Max Activating Token Index: 108

Text #4

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.4642. Min Act: -0.1700

Data Index: 7207733 (Open Web Text)

Max Activating Token Index: 691

Text #5

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.4616. Min Act: -0.1700

Data Index: 7468224 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.4520. Min Act: -0.1700

Data Index: 4812799 (Open Web Text)

Max Activating Token Index: 816

Text #7

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.4010. Min Act: -0.1700

Data Index: 1295747 (Open Web Text)

Max Activating Token Index: 649

Text #8

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.4090. Min Act: -0.1699

Data Index: 8643448 (Open Web Text)

Max Activating Token Index: 812

Text #9

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3536. Min Act: -0.1700

Data Index: 6279310 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3156. Min Act: -0.1700

Data Index: 3429498 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3424. Min Act: -0.1700

Data Index: 3654386 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3932. Min Act: -0.1700

Data Index: 3841880 (Open Web Text)

Max Activating Token Index: 661

Text #13

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.2985. Min Act: -0.1700

Data Index: 924962 (Open Web Text)

Max Activating Token Index: 606

Text #14

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3172. Min Act: -0.1692

Data Index: 1647685 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3839. Min Act: -0.1700

Data Index: 6214793 (Open Web Text)

Max Activating Token Index: 954

Text #16

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3181. Min Act: -0.1700

Data Index: 4871245 (Open Web Text)

Max Activating Token Index: 851

Text #17

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.3085. Min Act: -0.1700

Data Index: 289883 (Open Web Text)

Max Activating Token Index: 181

Text #18

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.2976. Min Act: -0.1700

Data Index: 1665740 (Open Web Text)

Max Activating Token Index: 694

Text #19

Max Range: 6.6907. Min Range: -6.6907

Max Act: 6.2572. Min Act: -0.1700

Data Index: 194680 (Open Web Text)

Max Activating Token Index: 372