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

Dataset: Open Web Text

Neuron 2109 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: 3.4619. Min Range: -3.4619

Max Act: 3.4619. Min Act: -0.1700

Data Index: 6090618 (Open Web Text)

Max Activating Token Index: 58

Text #1

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.4437. Min Act: -0.1700

Data Index: 4888287 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.3533. Min Act: -0.1700

Data Index: 4707873 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.3653. Min Act: -0.1700

Data Index: 1975985 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.1431. Min Act: -0.1700

Data Index: 4951838 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.1248. Min Act: -0.1700

Data Index: 6117037 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.1062. Min Act: -0.1700

Data Index: 2417776 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0913. Min Act: -0.1700

Data Index: 2209079 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0713. Min Act: -0.1700

Data Index: 2176149 (Open Web Text)

Max Activating Token Index: 833

Text #9

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0538. Min Act: -0.1700

Data Index: 8355354 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0422. Min Act: -0.1700

Data Index: 1575668 (Open Web Text)

Max Activating Token Index: 593

Text #11

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0257. Min Act: -0.1700

Data Index: 1159236 (Open Web Text)

Max Activating Token Index: 867

Text #12

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0095. Min Act: -0.1700

Data Index: 7133128 (Open Web Text)

Max Activating Token Index: 326

Text #13

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0114. Min Act: -0.1700

Data Index: 6989488 (Open Web Text)

Max Activating Token Index: 318

Text #14

Max Range: 3.4619. Min Range: -3.4619

Max Act: 2.9965. Min Act: -0.1700

Data Index: 5435990 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0301. Min Act: -0.1700

Data Index: 4332726 (Open Web Text)

Max Activating Token Index: 203

Text #16

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0063. Min Act: -0.1700

Data Index: 3605001 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 3.4619. Min Range: -3.4619

Max Act: 2.9791. Min Act: -0.1700

Data Index: 6519803 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 3.4619. Min Range: -3.4619

Max Act: 3.0023. Min Act: -0.1700

Data Index: 4001549 (Open Web Text)

Max Activating Token Index: 165

Text #19

Max Range: 3.4619. Min Range: -3.4619

Max Act: 2.9722. Min Act: -0.1700

Data Index: 4706217 (Open Web Text)

Max Activating Token Index: 728