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

Dataset: Open Web Text

Neuron 2648 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: 4.8766. Min Range: -4.8766

Max Act: 4.8766. Min Act: -0.1700

Data Index: 511657 (Open Web Text)

Max Activating Token Index: 301

Text #1

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.8643. Min Act: -0.1700

Data Index: 2694811 (Open Web Text)

Max Activating Token Index: 775

Text #2

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.8700. Min Act: -0.1700

Data Index: 7686533 (Open Web Text)

Max Activating Token Index: 712

Text #3

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.8213. Min Act: -0.1700

Data Index: 511656 (Open Web Text)

Max Activating Token Index: 513

Text #4

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.8674. Min Act: -0.1700

Data Index: 1993019 (Open Web Text)

Max Activating Token Index: 883

Text #5

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.7846. Min Act: -0.1700

Data Index: 3085161 (Open Web Text)

Max Activating Token Index: 968

Text #6

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.7240. Min Act: -0.1700

Data Index: 7146676 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.7551. Min Act: -0.1700

Data Index: 7701951 (Open Web Text)

Max Activating Token Index: 587

Text #8

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.7331. Min Act: -0.1700

Data Index: 124365 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.7175. Min Act: -0.1700

Data Index: 301512 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6968. Min Act: -0.1700

Data Index: 6022534 (Open Web Text)

Max Activating Token Index: 138

Text #11

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5887. Min Act: -0.1700

Data Index: 6148652 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6126. Min Act: -0.1700

Data Index: 483216 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6587. Min Act: -0.1700

Data Index: 6707681 (Open Web Text)

Max Activating Token Index: 515

Text #14

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6263. Min Act: -0.1700

Data Index: 7193748 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6015. Min Act: -0.1700

Data Index: 2204436 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6513. Min Act: -0.1700

Data Index: 7542278 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6145. Min Act: -0.1700

Data Index: 7146677 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.5498. Min Act: -0.1700

Data Index: 948390 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 4.8766. Min Range: -4.8766

Max Act: 4.6025. Min Act: -0.1700

Data Index: 7523793 (Open Web Text)

Max Activating Token Index: 107