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

Dataset: Open Web Text

Neuron 1380 in Layer 1

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: 4.8639. Min Range: -4.8639

Max Act: 4.8639. Min Act: -0.1700

Data Index: 3200816 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.8545. Min Act: -0.1700

Data Index: 6795396 (Open Web Text)

Max Activating Token Index: 209

Text #2

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.8137. Min Act: -0.1700

Data Index: 3553528 (Open Web Text)

Max Activating Token Index: 272

Text #3

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7955. Min Act: -0.1700

Data Index: 2776573 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7613. Min Act: -0.1700

Data Index: 5434521 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7610. Min Act: -0.1700

Data Index: 4451888 (Open Web Text)

Max Activating Token Index: 734

Text #6

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7244. Min Act: -0.1700

Data Index: 840077 (Open Web Text)

Max Activating Token Index: 628

Text #7

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7032. Min Act: -0.1700

Data Index: 4735099 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7081. Min Act: -0.1700

Data Index: 814182 (Open Web Text)

Max Activating Token Index: 340

Text #9

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7081. Min Act: -0.1700

Data Index: 3130680 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7139. Min Act: -0.1700

Data Index: 3032675 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.7048. Min Act: -0.1700

Data Index: 4051850 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6938. Min Act: -0.1700

Data Index: 3826682 (Open Web Text)

Max Activating Token Index: 597

Text #13

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6996. Min Act: -0.1700

Data Index: 1053723 (Open Web Text)

Max Activating Token Index: 740

Text #14

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6665. Min Act: -0.1700

Data Index: 6142816 (Open Web Text)

Max Activating Token Index: 64

Text #15

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6621. Min Act: -0.1700

Data Index: 2292164 (Open Web Text)

Max Activating Token Index: 315

Text #16

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6847. Min Act: -0.1700

Data Index: 780066 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6721. Min Act: -0.1700

Data Index: 3821264 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6766. Min Act: -0.1700

Data Index: 6142988 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 4.8639. Min Range: -4.8639

Max Act: 4.6646. Min Act: -0.1700

Data Index: 3278169 (Open Web Text)

Max Activating Token Index: 344