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

Dataset: Open Web Text

Neuron 103 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: 3.6288. Min Range: -3.6288

Max Act: 3.6288. Min Act: -0.1700

Data Index: 6605047 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4970. Min Act: -0.1700

Data Index: 4715329 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4466. Min Act: -0.1700

Data Index: 1938609 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4281. Min Act: -0.1700

Data Index: 2494309 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4143. Min Act: -0.1700

Data Index: 2191116 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4171. Min Act: -0.1700

Data Index: 6544647 (Open Web Text)

Max Activating Token Index: 712

Text #6

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3776. Min Act: -0.1700

Data Index: 3648790 (Open Web Text)

Max Activating Token Index: 892

Text #7

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3893. Min Act: -0.1700

Data Index: 5693593 (Open Web Text)

Max Activating Token Index: 241

Text #8

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3331. Min Act: -0.1700

Data Index: 7499073 (Open Web Text)

Max Activating Token Index: 1014

Text #9

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3514. Min Act: -0.1700

Data Index: 2969284 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3312. Min Act: -0.1700

Data Index: 306097 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3028. Min Act: -0.1700

Data Index: 4476284 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3383. Min Act: -0.1700

Data Index: 7243328 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3261. Min Act: -0.1700

Data Index: 798634 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3340. Min Act: -0.1700

Data Index: 743191 (Open Web Text)

Max Activating Token Index: 213

Text #15

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3293. Min Act: -0.1700

Data Index: 7074717 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3355. Min Act: -0.1700

Data Index: 4266631 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3035. Min Act: -0.1700

Data Index: 8044148 (Open Web Text)

Max Activating Token Index: 368

Text #18

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3110. Min Act: -0.1700

Data Index: 3610564 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3128. Min Act: -0.1700

Data Index: 3484207 (Open Web Text)

Max Activating Token Index: 202