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

Dataset: Open Web Text

Neuron 1944 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: 3.4150. Min Range: -3.4150

Max Act: 3.4150. Min Act: -0.1700

Data Index: 6355181 (Open Web Text)

Max Activating Token Index: 68

Text #1

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.4052. Min Act: -0.1700

Data Index: 6355178 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.3080. Min Act: -0.1700

Data Index: 376132 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.2266. Min Act: -0.1700

Data Index: 6355176 (Open Web Text)

Max Activating Token Index: 398

Text #4

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.2158. Min Act: -0.1700

Data Index: 6355175 (Open Web Text)

Max Activating Token Index: 391

Text #5

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.2366. Min Act: -0.1700

Data Index: 4171114 (Open Web Text)

Max Activating Token Index: 722

Text #6

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.2230. Min Act: -0.1700

Data Index: 6355174 (Open Web Text)

Max Activating Token Index: 382

Text #7

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.1280. Min Act: -0.1700

Data Index: 8734619 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.1211. Min Act: -0.1700

Data Index: 7705022 (Open Web Text)

Max Activating Token Index: 329

Text #9

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0983. Min Act: -0.1700

Data Index: 2003065 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.1034. Min Act: -0.1700

Data Index: 1095067 (Open Web Text)

Max Activating Token Index: 148

Text #11

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.1151. Min Act: -0.1700

Data Index: 4962885 (Open Web Text)

Max Activating Token Index: 1021

Text #12

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0844. Min Act: -0.1700

Data Index: 7040990 (Open Web Text)

Max Activating Token Index: 687

Text #13

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0636. Min Act: -0.1700

Data Index: 6355173 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0925. Min Act: -0.1700

Data Index: 7254010 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0429. Min Act: -0.1700

Data Index: 6338035 (Open Web Text)

Max Activating Token Index: 868

Text #16

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0465. Min Act: -0.1700

Data Index: 3354664 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0518. Min Act: -0.1700

Data Index: 8058830 (Open Web Text)

Max Activating Token Index: 984

Text #18

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0186. Min Act: -0.1700

Data Index: 3649622 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 3.4150. Min Range: -3.4150

Max Act: 3.0264. Min Act: -0.1700

Data Index: 4723090 (Open Web Text)

Max Activating Token Index: 730