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

Dataset: Open Web Text

Neuron 1458 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: 5.2743. Min Range: -5.2743

Max Act: 5.2743. Min Act: -0.1700

Data Index: 8198055 (Open Web Text)

Max Activating Token Index: 254

Text #1

Max Range: 5.2743. Min Range: -5.2743

Max Act: 5.0611. Min Act: -0.1700

Data Index: 4736390 (Open Web Text)

Max Activating Token Index: 124

Text #2

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.9993. Min Act: -0.1700

Data Index: 6840985 (Open Web Text)

Max Activating Token Index: 248

Text #3

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.9917. Min Act: -0.1700

Data Index: 5363262 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.9200. Min Act: -0.1700

Data Index: 5621575 (Open Web Text)

Max Activating Token Index: 393

Text #5

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.9113. Min Act: -0.1700

Data Index: 3305303 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8584. Min Act: -0.1700

Data Index: 7527444 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8754. Min Act: -0.1700

Data Index: 548213 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8843. Min Act: -0.1700

Data Index: 1384419 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8784. Min Act: -0.1700

Data Index: 548214 (Open Web Text)

Max Activating Token Index: 123

Text #10

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8825. Min Act: -0.1700

Data Index: 5627289 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8598. Min Act: -0.1700

Data Index: 8165248 (Open Web Text)

Max Activating Token Index: 403

Text #12

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8515. Min Act: -0.1700

Data Index: 8593877 (Open Web Text)

Max Activating Token Index: 970

Text #13

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8417. Min Act: -0.1700

Data Index: 1953805 (Open Web Text)

Max Activating Token Index: 551

Text #14

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8277. Min Act: -0.1700

Data Index: 5109533 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8089. Min Act: -0.1700

Data Index: 3840345 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8333. Min Act: -0.1700

Data Index: 7774319 (Open Web Text)

Max Activating Token Index: 901

Text #17

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8345. Min Act: -0.1700

Data Index: 6366080 (Open Web Text)

Max Activating Token Index: 844

Text #18

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.8319. Min Act: -0.1700

Data Index: 7364352 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 5.2743. Min Range: -5.2743

Max Act: 4.7986. Min Act: -0.1700

Data Index: 4241720 (Open Web Text)

Max Activating Token Index: 1020