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

Dataset: Open Web Text

Neuron 398 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: 4.6757. Min Range: -4.6757

Max Act: 4.6757. Min Act: -0.1700

Data Index: 8601857 (Open Web Text)

Max Activating Token Index: 262

Text #1

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.5670. Min Act: -0.1700

Data Index: 1043069 (Open Web Text)

Max Activating Token Index: 267

Text #2

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.5657. Min Act: -0.1700

Data Index: 1946254 (Open Web Text)

Max Activating Token Index: 915

Text #3

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.5477. Min Act: -0.1700

Data Index: 2164936 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4983. Min Act: -0.1700

Data Index: 8294448 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4467. Min Act: -0.1700

Data Index: 443112 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4285. Min Act: -0.1700

Data Index: 2355154 (Open Web Text)

Max Activating Token Index: 595

Text #7

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4660. Min Act: -0.1700

Data Index: 4505823 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4396. Min Act: -0.1700

Data Index: 5956475 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4040. Min Act: -0.1700

Data Index: 6566093 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4083. Min Act: -0.1700

Data Index: 711891 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4380. Min Act: -0.1700

Data Index: 7716075 (Open Web Text)

Max Activating Token Index: 627

Text #12

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.3698. Min Act: -0.1700

Data Index: 8118852 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4185. Min Act: -0.1700

Data Index: 2537672 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.3905. Min Act: -0.1700

Data Index: 6282709 (Open Web Text)

Max Activating Token Index: 703

Text #15

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.4041. Min Act: -0.1700

Data Index: 6882181 (Open Web Text)

Max Activating Token Index: 550

Text #16

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.3617. Min Act: -0.1700

Data Index: 3908352 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.3767. Min Act: -0.1700

Data Index: 5390046 (Open Web Text)

Max Activating Token Index: 731

Text #18

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.3912. Min Act: -0.1700

Data Index: 5086663 (Open Web Text)

Max Activating Token Index: 396

Text #19

Max Range: 4.6757. Min Range: -4.6757

Max Act: 4.3674. Min Act: -0.1700

Data Index: 4369404 (Open Web Text)

Max Activating Token Index: 381