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

Dataset: Open Web Text

Neuron 2921 in Layer 6

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: 3.6093. Min Range: -3.6093

Max Act: 3.6093. Min Act: -0.1700

Data Index: 6167775 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.5456. Min Act: -0.1700

Data Index: 5635576 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.5631. Min Act: -0.1700

Data Index: 3150770 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.5376. Min Act: -0.1700

Data Index: 8095253 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.5665. Min Act: -0.1700

Data Index: 5918459 (Open Web Text)

Max Activating Token Index: 778

Text #5

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.5236. Min Act: -0.1700

Data Index: 5635586 (Open Web Text)

Max Activating Token Index: 880

Text #6

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4967. Min Act: -0.1700

Data Index: 5266286 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.5186. Min Act: -0.1700

Data Index: 1701841 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.5338. Min Act: -0.1700

Data Index: 7596981 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4872. Min Act: -0.1700

Data Index: 5762859 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4700. Min Act: -0.1700

Data Index: 7832303 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4590. Min Act: -0.1700

Data Index: 4831780 (Open Web Text)

Max Activating Token Index: 926

Text #12

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4269. Min Act: -0.1700

Data Index: 6101173 (Open Web Text)

Max Activating Token Index: 641

Text #13

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4363. Min Act: -0.1700

Data Index: 2576183 (Open Web Text)

Max Activating Token Index: 700

Text #14

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4327. Min Act: -0.1700

Data Index: 6560460 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.3960. Min Act: -0.1700

Data Index: 6284904 (Open Web Text)

Max Activating Token Index: 374

Text #16

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.3990. Min Act: -0.1700

Data Index: 2061669 (Open Web Text)

Max Activating Token Index: 598

Text #17

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.3910. Min Act: -0.1700

Data Index: 6296919 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4131. Min Act: -0.1700

Data Index: 4661158 (Open Web Text)

Max Activating Token Index: 913

Text #19

Max Range: 3.6093. Min Range: -3.6093

Max Act: 3.4004. Min Act: -0.1700

Data Index: 1524857 (Open Web Text)

Max Activating Token Index: 978