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

Dataset: Open Web Text

Neuron 1321 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: 4.9740. Min Range: -4.9740

Max Act: 4.9740. Min Act: -0.1700

Data Index: 7779681 (Open Web Text)

Max Activating Token Index: 335

Text #1

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.9315. Min Act: -0.1700

Data Index: 2293583 (Open Web Text)

Max Activating Token Index: 879

Text #2

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.8936. Min Act: -0.1700

Data Index: 2232303 (Open Web Text)

Max Activating Token Index: 638

Text #3

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.7952. Min Act: -0.1700

Data Index: 3243069 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.7448. Min Act: -0.1700

Data Index: 7911156 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.8019. Min Act: -0.1700

Data Index: 4096522 (Open Web Text)

Max Activating Token Index: 316

Text #6

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.7428. Min Act: -0.1700

Data Index: 5587271 (Open Web Text)

Max Activating Token Index: 384

Text #7

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.7019. Min Act: -0.1700

Data Index: 8524677 (Open Web Text)

Max Activating Token Index: 416

Text #8

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.6892. Min Act: -0.1700

Data Index: 6855424 (Open Web Text)

Max Activating Token Index: 700

Text #9

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.7255. Min Act: -0.1700

Data Index: 1968294 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.6722. Min Act: -0.1700

Data Index: 6771344 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.7157. Min Act: -0.1700

Data Index: 5709948 (Open Web Text)

Max Activating Token Index: 805

Text #12

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.6081. Min Act: -0.1700

Data Index: 5733285 (Open Web Text)

Max Activating Token Index: 559

Text #13

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.6181. Min Act: -0.1700

Data Index: 883447 (Open Web Text)

Max Activating Token Index: 386

Text #14

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.5824. Min Act: -0.1700

Data Index: 1752156 (Open Web Text)

Max Activating Token Index: 434

Text #15

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.5769. Min Act: -0.1700

Data Index: 1741353 (Open Web Text)

Max Activating Token Index: 191

Text #16

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.5625. Min Act: -0.1700

Data Index: 6664330 (Open Web Text)

Max Activating Token Index: 746

Text #17

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.6121. Min Act: -0.1700

Data Index: 5670752 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.5495. Min Act: -0.1700

Data Index: 2955199 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 4.9740. Min Range: -4.9740

Max Act: 4.5718. Min Act: -0.1700

Data Index: 2211084 (Open Web Text)

Max Activating Token Index: 584