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

Dataset: Open Web Text

Neuron 1573 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: 4.7700. Min Range: -4.7700

Max Act: 4.7700. Min Act: -0.1700

Data Index: 397086 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.7418. Min Act: -0.1700

Data Index: 6664025 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.6318. Min Act: -0.1700

Data Index: 2880829 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.6447. Min Act: -0.1700

Data Index: 5993264 (Open Web Text)

Max Activating Token Index: 391

Text #4

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5924. Min Act: -0.1700

Data Index: 7516054 (Open Web Text)

Max Activating Token Index: 179

Text #5

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5935. Min Act: -0.1700

Data Index: 7499114 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5670. Min Act: -0.1700

Data Index: 5034049 (Open Web Text)

Max Activating Token Index: 555

Text #7

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5485. Min Act: -0.1700

Data Index: 3301819 (Open Web Text)

Max Activating Token Index: 413

Text #8

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5600. Min Act: -0.1700

Data Index: 1285598 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5281. Min Act: -0.1700

Data Index: 8505217 (Open Web Text)

Max Activating Token Index: 381

Text #10

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5220. Min Act: -0.1700

Data Index: 6782357 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5077. Min Act: -0.1700

Data Index: 5175846 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5401. Min Act: -0.1700

Data Index: 3734009 (Open Web Text)

Max Activating Token Index: 397

Text #13

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5305. Min Act: -0.1700

Data Index: 7788405 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.4995. Min Act: -0.1700

Data Index: 7347780 (Open Web Text)

Max Activating Token Index: 231

Text #15

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.4925. Min Act: -0.1700

Data Index: 3763609 (Open Web Text)

Max Activating Token Index: 345

Text #16

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.4585. Min Act: -0.1700

Data Index: 5406654 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5021. Min Act: -0.1700

Data Index: 2073876 (Open Web Text)

Max Activating Token Index: 214

Text #18

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5076. Min Act: -0.1700

Data Index: 2446980 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 4.7700. Min Range: -4.7700

Max Act: 4.5184. Min Act: -0.1700

Data Index: 5095852 (Open Web Text)

Max Activating Token Index: 264