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

Dataset: Open Web Text

Neuron 263 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: 3.8440. Min Range: -3.8440

Max Act: 3.8051. Min Act: -0.1700

Data Index: 61537 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.8246. Min Act: -0.1700

Data Index: 1217159 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.8006. Min Act: -0.1700

Data Index: 6114954 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.8440. Min Act: -0.1700

Data Index: 4539984 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7855. Min Act: -0.1700

Data Index: 4697740 (Open Web Text)

Max Activating Token Index: 548

Text #5

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7727. Min Act: -0.1700

Data Index: 1546248 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7901. Min Act: -0.1700

Data Index: 270175 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7911. Min Act: -0.1700

Data Index: 846433 (Open Web Text)

Max Activating Token Index: 298

Text #8

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7827. Min Act: -0.1699

Data Index: 4976702 (Open Web Text)

Max Activating Token Index: 996

Text #9

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7848. Min Act: -0.1700

Data Index: 1005561 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7876. Min Act: -0.1700

Data Index: 6239772 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.8037. Min Act: -0.1700

Data Index: 5471818 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7534. Min Act: -0.1700

Data Index: 6434349 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7425. Min Act: -0.1700

Data Index: 1425791 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7711. Min Act: -0.1700

Data Index: 8443819 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7091. Min Act: -0.1700

Data Index: 3544659 (Open Web Text)

Max Activating Token Index: 1007

Text #16

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7545. Min Act: -0.1700

Data Index: 5043348 (Open Web Text)

Max Activating Token Index: 714

Text #17

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7547. Min Act: -0.1700

Data Index: 1932690 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7297. Min Act: -0.1700

Data Index: 4798165 (Open Web Text)

Max Activating Token Index: 310

Text #19

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7195. Min Act: -0.1700

Data Index: 1217110 (Open Web Text)

Max Activating Token Index: 465