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

Dataset: Open Web Text

Neuron 3017 in Layer 5

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: 4.5347. Min Range: -4.5347

Max Act: 4.5347. Min Act: -0.1700

Data Index: 3968616 (Open Web Text)

Max Activating Token Index: 868

Text #1

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.4435. Min Act: -0.1700

Data Index: 1438391 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.4395. Min Act: -0.1700

Data Index: 3160955 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3448. Min Act: -0.1700

Data Index: 3883213 (Open Web Text)

Max Activating Token Index: 165

Text #4

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3629. Min Act: -0.1700

Data Index: 103421 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3544. Min Act: -0.1700

Data Index: 103433 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3709. Min Act: -0.1700

Data Index: 4701777 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3942. Min Act: -0.1700

Data Index: 5951190 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3783. Min Act: -0.1700

Data Index: 103431 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3131. Min Act: -0.1700

Data Index: 5123620 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3601. Min Act: -0.1700

Data Index: 1135211 (Open Web Text)

Max Activating Token Index: 277

Text #11

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.2886. Min Act: -0.1700

Data Index: 3681738 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3166. Min Act: -0.1700

Data Index: 103425 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3237. Min Act: -0.1700

Data Index: 7296000 (Open Web Text)

Max Activating Token Index: 612

Text #14

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3170. Min Act: -0.1700

Data Index: 103434 (Open Web Text)

Max Activating Token Index: 119

Text #15

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.3144. Min Act: -0.1700

Data Index: 103435 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.2949. Min Act: -0.1700

Data Index: 103436 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.2849. Min Act: -0.1700

Data Index: 1003227 (Open Web Text)

Max Activating Token Index: 640

Text #18

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.2820. Min Act: -0.1700

Data Index: 2458920 (Open Web Text)

Max Activating Token Index: 726

Text #19

Max Range: 4.5347. Min Range: -4.5347

Max Act: 4.2915. Min Act: -0.1700

Data Index: 103424 (Open Web Text)

Max Activating Token Index: 18