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

Dataset: Open Web Text

Neuron 1384 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: 2.9132. Min Range: -2.9132

Max Act: 2.9132. Min Act: -0.1700

Data Index: 5289091 (Open Web Text)

Max Activating Token Index: 859

Text #1

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.9125. Min Act: -0.1700

Data Index: 1828809 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8741. Min Act: -0.1700

Data Index: 4182421 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8563. Min Act: -0.1700

Data Index: 1242234 (Open Web Text)

Max Activating Token Index: 525

Text #4

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8669. Min Act: -0.1700

Data Index: 7787369 (Open Web Text)

Max Activating Token Index: 628

Text #5

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8643. Min Act: -0.1700

Data Index: 601263 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8657. Min Act: -0.1700

Data Index: 3425122 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8490. Min Act: -0.1700

Data Index: 3086106 (Open Web Text)

Max Activating Token Index: 731

Text #8

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8659. Min Act: -0.1700

Data Index: 2620957 (Open Web Text)

Max Activating Token Index: 926

Text #9

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8645. Min Act: -0.1700

Data Index: 6585099 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8600. Min Act: -0.1700

Data Index: 1978942 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8491. Min Act: -0.1700

Data Index: 6634057 (Open Web Text)

Max Activating Token Index: 812

Text #12

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8632. Min Act: -0.1700

Data Index: 6382585 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8387. Min Act: -0.1700

Data Index: 2379356 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8486. Min Act: -0.1700

Data Index: 3250627 (Open Web Text)

Max Activating Token Index: 487

Text #15

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8502. Min Act: -0.1700

Data Index: 3268806 (Open Web Text)

Max Activating Token Index: 348

Text #16

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8249. Min Act: -0.1700

Data Index: 5836101 (Open Web Text)

Max Activating Token Index: 896

Text #17

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8129. Min Act: -0.1700

Data Index: 3089251 (Open Web Text)

Max Activating Token Index: 474

Text #18

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8254. Min Act: -0.1700

Data Index: 4342623 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8367. Min Act: -0.1700

Data Index: 4158843 (Open Web Text)

Max Activating Token Index: 948