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

Dataset: Open Web Text

Neuron 725 in Layer 3

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: 4.8394. Min Range: -4.8394

Max Act: 4.8394. Min Act: -0.1700

Data Index: 1075946 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7810. Min Act: -0.1700

Data Index: 173178 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7669. Min Act: -0.1700

Data Index: 1968650 (Open Web Text)

Max Activating Token Index: 124

Text #3

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7815. Min Act: -0.1700

Data Index: 7003458 (Open Web Text)

Max Activating Token Index: 866

Text #4

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7814. Min Act: -0.1700

Data Index: 4849113 (Open Web Text)

Max Activating Token Index: 447

Text #5

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7157. Min Act: -0.1700

Data Index: 7481848 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7099. Min Act: -0.1700

Data Index: 6013904 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6722. Min Act: -0.1700

Data Index: 8039012 (Open Web Text)

Max Activating Token Index: 108

Text #8

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7151. Min Act: -0.1700

Data Index: 8538629 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5995. Min Act: -0.1700

Data Index: 4651790 (Open Web Text)

Max Activating Token Index: 146

Text #10

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6146. Min Act: -0.1700

Data Index: 7978339 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6166. Min Act: -0.1700

Data Index: 4868768 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6475. Min Act: -0.1700

Data Index: 2323271 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5847. Min Act: -0.1700

Data Index: 3587404 (Open Web Text)

Max Activating Token Index: 721

Text #14

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6574. Min Act: -0.1700

Data Index: 1610536 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5820. Min Act: -0.1700

Data Index: 8649560 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6157. Min Act: -0.1700

Data Index: 5015690 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6194. Min Act: -0.1700

Data Index: 840117 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5469. Min Act: -0.1700

Data Index: 4911858 (Open Web Text)

Max Activating Token Index: 571

Text #19

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6015. Min Act: -0.1700

Data Index: 2886322 (Open Web Text)

Max Activating Token Index: 442