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

Dataset: Open Web Text

Neuron 543 in Layer 1

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: 3.6730. Min Range: -3.6730

Max Act: 3.6730. Min Act: -0.1700

Data Index: 5443630 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6585. Min Act: -0.1700

Data Index: 719852 (Open Web Text)

Max Activating Token Index: 436

Text #2

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6419. Min Act: -0.1700

Data Index: 8369178 (Open Web Text)

Max Activating Token Index: 712

Text #3

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6564. Min Act: -0.1700

Data Index: 6722838 (Open Web Text)

Max Activating Token Index: 197

Text #4

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6559. Min Act: -0.1700

Data Index: 6246648 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6492. Min Act: -0.1700

Data Index: 5545912 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6493. Min Act: -0.1700

Data Index: 95677 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6441. Min Act: -0.1700

Data Index: 4709258 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6455. Min Act: -0.1700

Data Index: 2813234 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6404. Min Act: -0.1700

Data Index: 8378045 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6199. Min Act: -0.1700

Data Index: 5007569 (Open Web Text)

Max Activating Token Index: 512

Text #11

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6093. Min Act: -0.1700

Data Index: 5491050 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6267. Min Act: -0.1700

Data Index: 1030205 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6233. Min Act: -0.1700

Data Index: 4799982 (Open Web Text)

Max Activating Token Index: 767

Text #14

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.5958. Min Act: -0.1700

Data Index: 6072579 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6071. Min Act: -0.1700

Data Index: 788430 (Open Web Text)

Max Activating Token Index: 328

Text #16

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6101. Min Act: -0.1700

Data Index: 6205940 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6120. Min Act: -0.1700

Data Index: 6221494 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.5954. Min Act: -0.1700

Data Index: 959537 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 3.6730. Min Range: -3.6730

Max Act: 3.6050. Min Act: -0.1700

Data Index: 7545476 (Open Web Text)

Max Activating Token Index: 451