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

Dataset: Open Web Text

Neuron 713 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: 0.5197. Min Range: -0.5197

Max Act: 0.5197. Min Act: -0.1699

Data Index: 8733306 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4502. Min Act: -0.1700

Data Index: 2959638 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4164. Min Act: -0.1700

Data Index: 4568720 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3746. Min Act: -0.1700

Data Index: 6735979 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3532. Min Act: -0.1694

Data Index: 2633753 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3521. Min Act: -0.1700

Data Index: 1227122 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3300. Min Act: -0.1696

Data Index: 1648478 (Open Web Text)

Max Activating Token Index: 861

Text #7

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3278. Min Act: -0.1700

Data Index: 6111242 (Open Web Text)

Max Activating Token Index: 462

Text #8

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3185. Min Act: -0.1700

Data Index: 1249153 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3084. Min Act: -0.1700

Data Index: 3963182 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3264. Min Act: -0.1700

Data Index: 551404 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3079. Min Act: -0.1700

Data Index: 2845307 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3119. Min Act: -0.1699

Data Index: 7827119 (Open Web Text)

Max Activating Token Index: 292

Text #13

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3069. Min Act: -0.1700

Data Index: 3701657 (Open Web Text)

Max Activating Token Index: 823

Text #14

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2947. Min Act: -0.1699

Data Index: 6145400 (Open Web Text)

Max Activating Token Index: 245

Text #15

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2840. Min Act: -0.1606

Data Index: 1487252 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2874. Min Act: -0.1700

Data Index: 2160317 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2958. Min Act: -0.1700

Data Index: 4645386 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2881. Min Act: -0.1700

Data Index: 3431568 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2821. Min Act: -0.1700

Data Index: 7469353 (Open Web Text)

Max Activating Token Index: 65