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

Dataset: Open Web Text

Neuron 2841 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: 4.9462. Min Range: -4.9462

Max Act: 4.9462. Min Act: -0.1700

Data Index: 4812706 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.8787. Min Act: -0.1700

Data Index: 4533218 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.8368. Min Act: -0.1700

Data Index: 2466974 (Open Web Text)

Max Activating Token Index: 548

Text #3

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.8249. Min Act: -0.1700

Data Index: 5627835 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.8218. Min Act: -0.1700

Data Index: 1493686 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.8387. Min Act: -0.1700

Data Index: 5683365 (Open Web Text)

Max Activating Token Index: 966

Text #6

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7988. Min Act: -0.1700

Data Index: 6056116 (Open Web Text)

Max Activating Token Index: 214

Text #7

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7943. Min Act: -0.1700

Data Index: 2531449 (Open Web Text)

Max Activating Token Index: 690

Text #8

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.8091. Min Act: -0.1700

Data Index: 2777881 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7983. Min Act: -0.1700

Data Index: 2930269 (Open Web Text)

Max Activating Token Index: 85

Text #10

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7673. Min Act: -0.1700

Data Index: 3342754 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7529. Min Act: -0.1700

Data Index: 7590232 (Open Web Text)

Max Activating Token Index: 654

Text #12

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7624. Min Act: -0.1700

Data Index: 6742581 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7709. Min Act: -0.1700

Data Index: 4336302 (Open Web Text)

Max Activating Token Index: 169

Text #14

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7747. Min Act: -0.1700

Data Index: 5958534 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7590. Min Act: -0.1700

Data Index: 5801494 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7500. Min Act: -0.1700

Data Index: 888109 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7792. Min Act: -0.1700

Data Index: 5786548 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7579. Min Act: -0.1700

Data Index: 2515726 (Open Web Text)

Max Activating Token Index: 94

Text #19

Max Range: 4.9462. Min Range: -4.9462

Max Act: 4.7663. Min Act: -0.1700

Data Index: 1147471 (Open Web Text)

Max Activating Token Index: 207