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

Dataset: Open Web Text

Neuron 3022 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: 3.7027. Min Range: -3.7027

Max Act: 3.7027. Min Act: -0.1700

Data Index: 111647 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4948. Min Act: -0.1700

Data Index: 2088911 (Open Web Text)

Max Activating Token Index: 188

Text #2

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4393. Min Act: -0.1700

Data Index: 2704664 (Open Web Text)

Max Activating Token Index: 578

Text #3

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4369. Min Act: -0.1700

Data Index: 2403703 (Open Web Text)

Max Activating Token Index: 704

Text #4

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4310. Min Act: -0.1700

Data Index: 8786888 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.3351. Min Act: -0.1700

Data Index: 5374804 (Open Web Text)

Max Activating Token Index: 146

Text #6

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.3310. Min Act: -0.1700

Data Index: 396053 (Open Web Text)

Max Activating Token Index: 415

Text #7

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.3011. Min Act: -0.1700

Data Index: 2834333 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.3128. Min Act: -0.1700

Data Index: 7539269 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.2881. Min Act: -0.1700

Data Index: 2704665 (Open Web Text)

Max Activating Token Index: 289

Text #10

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.2624. Min Act: -0.1700

Data Index: 3851406 (Open Web Text)

Max Activating Token Index: 820

Text #11

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.2574. Min Act: -0.1700

Data Index: 3077758 (Open Web Text)

Max Activating Token Index: 646

Text #12

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.2630. Min Act: -0.1700

Data Index: 7189078 (Open Web Text)

Max Activating Token Index: 720

Text #13

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.1968. Min Act: -0.1700

Data Index: 4229203 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.1927. Min Act: -0.1700

Data Index: 4216918 (Open Web Text)

Max Activating Token Index: 717

Text #15

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.1878. Min Act: -0.1700

Data Index: 7884924 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.1784. Min Act: -0.1700

Data Index: 2892561 (Open Web Text)

Max Activating Token Index: 359

Text #17

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.1786. Min Act: -0.1700

Data Index: 4101814 (Open Web Text)

Max Activating Token Index: 115

Text #18

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.1605. Min Act: -0.1700

Data Index: 4095674 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.1582. Min Act: -0.1700

Data Index: 4358388 (Open Web Text)

Max Activating Token Index: 108