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

Dataset: Open Web Text

Neuron 2542 in Layer 0

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: 1.4766. Min Range: -1.4766

Max Act: 1.4766. Min Act: -0.1700

Data Index: 5025443 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4605. Min Act: -0.1700

Data Index: 984754 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4479. Min Act: -0.1700

Data Index: 4568849 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4209. Min Act: -0.1700

Data Index: 6087132 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4325. Min Act: -0.1700

Data Index: 7865314 (Open Web Text)

Max Activating Token Index: 1007

Text #5

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4313. Min Act: -0.1700

Data Index: 5865468 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4080. Min Act: -0.1700

Data Index: 7360441 (Open Web Text)

Max Activating Token Index: 1014

Text #7

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4137. Min Act: -0.1700

Data Index: 2585245 (Open Web Text)

Max Activating Token Index: 563

Text #8

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4081. Min Act: -0.1700

Data Index: 1534552 (Open Web Text)

Max Activating Token Index: 1011

Text #9

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4147. Min Act: -0.1700

Data Index: 7865312 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3942. Min Act: -0.1700

Data Index: 2018657 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3961. Min Act: -0.1700

Data Index: 7154902 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3990. Min Act: -0.1700

Data Index: 1004708 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3748. Min Act: -0.1700

Data Index: 2282722 (Open Web Text)

Max Activating Token Index: 512

Text #14

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3805. Min Act: -0.1700

Data Index: 4442279 (Open Web Text)

Max Activating Token Index: 544

Text #15

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3737. Min Act: -0.1700

Data Index: 1226885 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3867. Min Act: -0.1700

Data Index: 6380308 (Open Web Text)

Max Activating Token Index: 497

Text #17

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3513. Min Act: -0.1700

Data Index: 4317892 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3638. Min Act: -0.1700

Data Index: 1503804 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3360. Min Act: -0.1700

Data Index: 3824264 (Open Web Text)

Max Activating Token Index: 992