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

Dataset: Open Web Text

Neuron 2141 in Layer 4

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: 3.4467. Min Range: -3.4467

Max Act: 3.4467. Min Act: -0.1700

Data Index: 6654398 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.4186. Min Act: -0.1700

Data Index: 1952472 (Open Web Text)

Max Activating Token Index: 179

Text #2

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.4109. Min Act: -0.1700

Data Index: 4331807 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3988. Min Act: -0.1700

Data Index: 4850758 (Open Web Text)

Max Activating Token Index: 65

Text #4

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3887. Min Act: -0.1700

Data Index: 7302215 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3513. Min Act: -0.1700

Data Index: 202738 (Open Web Text)

Max Activating Token Index: 169

Text #6

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3439. Min Act: -0.1700

Data Index: 7806627 (Open Web Text)

Max Activating Token Index: 843

Text #7

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3650. Min Act: -0.1700

Data Index: 6280086 (Open Web Text)

Max Activating Token Index: 905

Text #8

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3312. Min Act: -0.1700

Data Index: 2383532 (Open Web Text)

Max Activating Token Index: 26

Text #9

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3349. Min Act: -0.1700

Data Index: 3417693 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3401. Min Act: -0.1700

Data Index: 2443852 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3373. Min Act: -0.1700

Data Index: 6187370 (Open Web Text)

Max Activating Token Index: 485

Text #12

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3106. Min Act: -0.1700

Data Index: 6484793 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3217. Min Act: -0.1700

Data Index: 5259280 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3064. Min Act: -0.1700

Data Index: 7675132 (Open Web Text)

Max Activating Token Index: 794

Text #15

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3111. Min Act: -0.1700

Data Index: 8555033 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3138. Min Act: -0.1700

Data Index: 7862776 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1813885 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.3271. Min Act: -0.1700

Data Index: 3810241 (Open Web Text)

Max Activating Token Index: 907

Text #19

Max Range: 3.4467. Min Range: -3.4467

Max Act: 3.2497. Min Act: -0.1700

Data Index: 5737285 (Open Web Text)

Max Activating Token Index: 455