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

Dataset: Open Web Text

Neuron 476 in Layer 5

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: 3.1685. Min Range: -3.1685

Max Act: 3.1521. Min Act: -0.1700

Data Index: 5893316 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 3.1685. Min Range: -3.1685

Max Act: 3.1685. Min Act: -0.1700

Data Index: 7472203 (Open Web Text)

Max Activating Token Index: 479

Text #2

Max Range: 3.1685. Min Range: -3.1685

Max Act: 3.0325. Min Act: -0.1700

Data Index: 1410644 (Open Web Text)

Max Activating Token Index: 766

Text #3

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9838. Min Act: -0.1700

Data Index: 922035 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9680. Min Act: -0.1700

Data Index: 6264476 (Open Web Text)

Max Activating Token Index: 637

Text #5

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9471. Min Act: -0.1700

Data Index: 6576479 (Open Web Text)

Max Activating Token Index: 792

Text #6

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9304. Min Act: -0.1700

Data Index: 8712790 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9320. Min Act: -0.1700

Data Index: 6516354 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9008. Min Act: -0.1700

Data Index: 422608 (Open Web Text)

Max Activating Token Index: 383

Text #9

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9319. Min Act: -0.1700

Data Index: 6177308 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9018. Min Act: -0.1700

Data Index: 5583364 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9215. Min Act: -0.1700

Data Index: 4175025 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9029. Min Act: -0.1700

Data Index: 4731008 (Open Web Text)

Max Activating Token Index: 907

Text #13

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9378. Min Act: -0.1700

Data Index: 7180627 (Open Web Text)

Max Activating Token Index: 743

Text #14

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.8907. Min Act: -0.1700

Data Index: 734528 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9038. Min Act: -0.1700

Data Index: 8771586 (Open Web Text)

Max Activating Token Index: 109

Text #16

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9122. Min Act: -0.1700

Data Index: 4814121 (Open Web Text)

Max Activating Token Index: 152

Text #17

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.9048. Min Act: -0.1700

Data Index: 5171257 (Open Web Text)

Max Activating Token Index: 32

Text #18

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.8884. Min Act: -0.1700

Data Index: 3685715 (Open Web Text)

Max Activating Token Index: 171

Text #19

Max Range: 3.1685. Min Range: -3.1685

Max Act: 2.8922. Min Act: -0.1700

Data Index: 6304074 (Open Web Text)

Max Activating Token Index: 774