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

Dataset: Open Web Text

Neuron 455 in Layer 3

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: 3.5988. Min Range: -3.5988

Max Act: 3.5988. Min Act: -0.1700

Data Index: 329198 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5254. Min Act: -0.1700

Data Index: 8050590 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5536. Min Act: -0.1700

Data Index: 7717623 (Open Web Text)

Max Activating Token Index: 649

Text #3

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.5019. Min Act: -0.1700

Data Index: 8076803 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.4200. Min Act: -0.1700

Data Index: 5981156 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3232. Min Act: -0.1700

Data Index: 224992 (Open Web Text)

Max Activating Token Index: 252

Text #6

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3215. Min Act: -0.1700

Data Index: 542507 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3140. Min Act: -0.1700

Data Index: 742912 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3072. Min Act: -0.1700

Data Index: 1450798 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3063. Min Act: -0.1700

Data Index: 4833286 (Open Web Text)

Max Activating Token Index: 416

Text #10

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.2750. Min Act: -0.1700

Data Index: 4495084 (Open Web Text)

Max Activating Token Index: 480

Text #11

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.2911. Min Act: -0.1700

Data Index: 7934999 (Open Web Text)

Max Activating Token Index: 620

Text #12

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3286. Min Act: -0.1700

Data Index: 2147947 (Open Web Text)

Max Activating Token Index: 468

Text #13

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3015. Min Act: -0.1700

Data Index: 5649218 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.2994. Min Act: -0.1700

Data Index: 2011906 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3618. Min Act: -0.1700

Data Index: 939163 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3071. Min Act: -0.1700

Data Index: 5509580 (Open Web Text)

Max Activating Token Index: 831

Text #17

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.3054. Min Act: -0.1700

Data Index: 5346439 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.2699. Min Act: -0.1700

Data Index: 4589297 (Open Web Text)

Max Activating Token Index: 528

Text #19

Max Range: 3.5988. Min Range: -3.5988

Max Act: 3.2227. Min Act: -0.1700

Data Index: 2774522 (Open Web Text)

Max Activating Token Index: 450