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

Dataset: Open Web Text

Neuron 1380 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: 3.4046. Min Range: -3.4046

Max Act: 3.4046. Min Act: -0.1700

Data Index: 5873768 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3551. Min Act: -0.1700

Data Index: 1933051 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3063. Min Act: -0.1700

Data Index: 8475434 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3065. Min Act: -0.1700

Data Index: 6305373 (Open Web Text)

Max Activating Token Index: 901

Text #4

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3032. Min Act: -0.1700

Data Index: 1860093 (Open Web Text)

Max Activating Token Index: 745

Text #5

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2909. Min Act: -0.1700

Data Index: 5677886 (Open Web Text)

Max Activating Token Index: 423

Text #6

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2551. Min Act: -0.1700

Data Index: 1752899 (Open Web Text)

Max Activating Token Index: 421

Text #7

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3015. Min Act: -0.1700

Data Index: 5338897 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2839. Min Act: -0.1700

Data Index: 3888878 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2952. Min Act: -0.1700

Data Index: 5186468 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2647. Min Act: -0.1700

Data Index: 7448382 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2581. Min Act: -0.1700

Data Index: 4183118 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2717. Min Act: -0.1700

Data Index: 3270102 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2539. Min Act: -0.1700

Data Index: 6071693 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2318. Min Act: -0.1700

Data Index: 2269276 (Open Web Text)

Max Activating Token Index: 1008

Text #15

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2272. Min Act: -0.1700

Data Index: 943734 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2428. Min Act: -0.1700

Data Index: 3556130 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2411. Min Act: -0.1700

Data Index: 5209156 (Open Web Text)

Max Activating Token Index: 731

Text #18

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2549. Min Act: -0.1700

Data Index: 7148570 (Open Web Text)

Max Activating Token Index: 974

Text #19

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2291. Min Act: -0.1700

Data Index: 5172387 (Open Web Text)

Max Activating Token Index: 348