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

Dataset: Open Web Text

Neuron 14 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: 3.1441. Min Range: -3.1441

Max Act: 3.1441. Min Act: -0.1700

Data Index: 643453 (Open Web Text)

Max Activating Token Index: 288

Text #1

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0833. Min Act: -0.1700

Data Index: 4480656 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0844. Min Act: -0.1700

Data Index: 5181348 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0716. Min Act: -0.1700

Data Index: 6702187 (Open Web Text)

Max Activating Token Index: 141

Text #4

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.1001. Min Act: -0.1700

Data Index: 195253 (Open Web Text)

Max Activating Token Index: 448

Text #5

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0696. Min Act: -0.1700

Data Index: 2009511 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0503. Min Act: -0.1700

Data Index: 7674338 (Open Web Text)

Max Activating Token Index: 542

Text #7

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0448. Min Act: -0.1700

Data Index: 1036460 (Open Web Text)

Max Activating Token Index: 537

Text #8

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9991. Min Act: -0.1700

Data Index: 2188138 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0082. Min Act: -0.1700

Data Index: 421048 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9935. Min Act: -0.1700

Data Index: 6450712 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9892. Min Act: -0.1700

Data Index: 3978177 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9929. Min Act: -0.1700

Data Index: 4495977 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9951. Min Act: -0.1700

Data Index: 595355 (Open Web Text)

Max Activating Token Index: 437

Text #14

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9779. Min Act: -0.1700

Data Index: 973812 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 3.1441. Min Range: -3.1441

Max Act: 3.0002. Min Act: -0.1700

Data Index: 1148202 (Open Web Text)

Max Activating Token Index: 411

Text #16

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9598. Min Act: -0.1700

Data Index: 5849016 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9661. Min Act: -0.1700

Data Index: 3298714 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9716. Min Act: -0.1700

Data Index: 4128848 (Open Web Text)

Max Activating Token Index: 99

Text #19

Max Range: 3.1441. Min Range: -3.1441

Max Act: 2.9874. Min Act: -0.1700

Data Index: 4858947 (Open Web Text)

Max Activating Token Index: 303