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

Dataset: Open Web Text

Neuron 795 in Layer 2

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: 4.8112. Min Range: -4.8112

Max Act: 4.8112. Min Act: -0.1700

Data Index: 6501350 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.6499. Min Act: -0.1700

Data Index: 71977 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.6098. Min Act: -0.1700

Data Index: 8273573 (Open Web Text)

Max Activating Token Index: 106

Text #3

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.5153. Min Act: -0.1700

Data Index: 2202768 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.5342. Min Act: -0.1700

Data Index: 7692549 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.5457. Min Act: -0.1700

Data Index: 7518744 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.5096. Min Act: -0.1700

Data Index: 8586025 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.4718. Min Act: -0.1700

Data Index: 7737413 (Open Web Text)

Max Activating Token Index: 573

Text #8

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.4496. Min Act: -0.1700

Data Index: 4876840 (Open Web Text)

Max Activating Token Index: 258

Text #9

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.4584. Min Act: -0.1700

Data Index: 2658311 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3922. Min Act: -0.1700

Data Index: 7270441 (Open Web Text)

Max Activating Token Index: 785

Text #11

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3843. Min Act: -0.1700

Data Index: 1248254 (Open Web Text)

Max Activating Token Index: 572

Text #12

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3815. Min Act: -0.1700

Data Index: 4212319 (Open Web Text)

Max Activating Token Index: 559

Text #13

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3575. Min Act: -0.1700

Data Index: 6501349 (Open Web Text)

Max Activating Token Index: 692

Text #14

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3270. Min Act: -0.1700

Data Index: 316877 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3801. Min Act: -0.1700

Data Index: 1894425 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3215. Min Act: -0.1700

Data Index: 3028895 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3112. Min Act: -0.1700

Data Index: 6557480 (Open Web Text)

Max Activating Token Index: 958

Text #18

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.2973. Min Act: -0.1700

Data Index: 7526141 (Open Web Text)

Max Activating Token Index: 809

Text #19

Max Range: 4.8112. Min Range: -4.8112

Max Act: 4.3369. Min Act: -0.1700

Data Index: 4975089 (Open Web Text)

Max Activating Token Index: 159