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

Dataset: Open Web Text

Neuron 864 in Layer 3

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: 3.9678. Min Range: -3.9678

Max Act: 3.9678. Min Act: -0.1700

Data Index: 6858318 (Open Web Text)

Max Activating Token Index: 380

Text #1

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8733. Min Act: -0.1700

Data Index: 911304 (Open Web Text)

Max Activating Token Index: 339

Text #2

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8642. Min Act: -0.1700

Data Index: 5055534 (Open Web Text)

Max Activating Token Index: 510

Text #3

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8991. Min Act: -0.1700

Data Index: 8162651 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.9162. Min Act: -0.1700

Data Index: 5571861 (Open Web Text)

Max Activating Token Index: 312

Text #5

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8976. Min Act: -0.1700

Data Index: 8522022 (Open Web Text)

Max Activating Token Index: 181

Text #6

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.9008. Min Act: -0.1700

Data Index: 5515637 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.9084. Min Act: -0.1700

Data Index: 78177 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8589. Min Act: -0.1700

Data Index: 2545365 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8721. Min Act: -0.1700

Data Index: 148849 (Open Web Text)

Max Activating Token Index: 632

Text #10

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8757. Min Act: -0.1700

Data Index: 3845348 (Open Web Text)

Max Activating Token Index: 883

Text #11

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8837. Min Act: -0.1700

Data Index: 3832749 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8797. Min Act: -0.1700

Data Index: 8023296 (Open Web Text)

Max Activating Token Index: 173

Text #13

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.9266. Min Act: -0.1700

Data Index: 7842599 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8438. Min Act: -0.1700

Data Index: 4502913 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.9223. Min Act: -0.1700

Data Index: 6282774 (Open Web Text)

Max Activating Token Index: 766

Text #16

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8917. Min Act: -0.1700

Data Index: 2729026 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8985. Min Act: -0.1700

Data Index: 4014706 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8821. Min Act: -0.1700

Data Index: 577904 (Open Web Text)

Max Activating Token Index: 302

Text #19

Max Range: 3.9678. Min Range: -3.9678

Max Act: 3.8866. Min Act: -0.1700

Data Index: 4260228 (Open Web Text)

Max Activating Token Index: 627