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

Dataset: Open Web Text

Neuron 670 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: 3.3547. Min Range: -3.3547

Max Act: 3.3547. Min Act: -0.1700

Data Index: 2280289 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3000. Min Act: -0.1700

Data Index: 4173459 (Open Web Text)

Max Activating Token Index: 561

Text #2

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3255. Min Act: -0.1700

Data Index: 5399340 (Open Web Text)

Max Activating Token Index: 640

Text #3

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3064. Min Act: -0.1700

Data Index: 6185486 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2956. Min Act: -0.1700

Data Index: 947065 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2590. Min Act: -0.1700

Data Index: 2821631 (Open Web Text)

Max Activating Token Index: 703

Text #6

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2678. Min Act: -0.1700

Data Index: 3683179 (Open Web Text)

Max Activating Token Index: 304

Text #7

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2378. Min Act: -0.1700

Data Index: 2660403 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2370. Min Act: -0.1700

Data Index: 7662997 (Open Web Text)

Max Activating Token Index: 424

Text #9

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2515. Min Act: -0.1700

Data Index: 8556214 (Open Web Text)

Max Activating Token Index: 201

Text #10

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2547. Min Act: -0.1700

Data Index: 4778007 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2346. Min Act: -0.1700

Data Index: 3635921 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2619. Min Act: -0.1700

Data Index: 1569105 (Open Web Text)

Max Activating Token Index: 695

Text #13

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2409. Min Act: -0.1700

Data Index: 4520208 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2215. Min Act: -0.1700

Data Index: 4625826 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2471. Min Act: -0.1700

Data Index: 2746892 (Open Web Text)

Max Activating Token Index: 155

Text #16

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2233. Min Act: -0.1700

Data Index: 6700941 (Open Web Text)

Max Activating Token Index: 717

Text #17

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2714. Min Act: -0.1700

Data Index: 1611151 (Open Web Text)

Max Activating Token Index: 923

Text #18

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2100. Min Act: -0.1700

Data Index: 5951790 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.1797. Min Act: -0.1700

Data Index: 51757 (Open Web Text)

Max Activating Token Index: 546