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

Dataset: Open Web Text

Neuron 1696 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: 3.9105. Min Range: -3.9105

Max Act: 3.9105. Min Act: -0.1700

Data Index: 5445959 (Open Web Text)

Max Activating Token Index: 746

Text #1

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8967. Min Act: -0.1700

Data Index: 188937 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8802. Min Act: -0.1700

Data Index: 1445359 (Open Web Text)

Max Activating Token Index: 206

Text #3

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8521. Min Act: -0.1700

Data Index: 178021 (Open Web Text)

Max Activating Token Index: 712

Text #4

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8272. Min Act: -0.1700

Data Index: 4156140 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8322. Min Act: -0.1700

Data Index: 121292 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8455. Min Act: -0.1700

Data Index: 1066492 (Open Web Text)

Max Activating Token Index: 533

Text #7

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7790. Min Act: -0.1700

Data Index: 524091 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.8046. Min Act: -0.1700

Data Index: 3181803 (Open Web Text)

Max Activating Token Index: 558

Text #9

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7923. Min Act: -0.1700

Data Index: 2918764 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7734. Min Act: -0.1700

Data Index: 7515119 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7343. Min Act: -0.1700

Data Index: 4437112 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7186. Min Act: -0.1700

Data Index: 5676592 (Open Web Text)

Max Activating Token Index: 603

Text #13

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7343. Min Act: -0.1700

Data Index: 335491 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7397. Min Act: -0.1700

Data Index: 8147023 (Open Web Text)

Max Activating Token Index: 709

Text #15

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7144. Min Act: -0.1700

Data Index: 1602703 (Open Web Text)

Max Activating Token Index: 738

Text #16

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7000. Min Act: -0.1700

Data Index: 3171533 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7029. Min Act: -0.1700

Data Index: 8276240 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7109. Min Act: -0.1700

Data Index: 2373189 (Open Web Text)

Max Activating Token Index: 809

Text #19

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7235. Min Act: -0.1700

Data Index: 5075006 (Open Web Text)

Max Activating Token Index: 545