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

Dataset: Open Web Text

Neuron 475 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: 4.8619. Min Range: -4.8619

Max Act: 4.8619. Min Act: -0.1700

Data Index: 8721485 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.8011. Min Act: -0.1700

Data Index: 5099165 (Open Web Text)

Max Activating Token Index: 652

Text #2

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.7571. Min Act: -0.1700

Data Index: 4238781 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6784. Min Act: -0.1700

Data Index: 4193516 (Open Web Text)

Max Activating Token Index: 797

Text #4

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.7250. Min Act: -0.1700

Data Index: 6508841 (Open Web Text)

Max Activating Token Index: 72

Text #5

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.7207. Min Act: -0.1700

Data Index: 2133231 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6967. Min Act: -0.1700

Data Index: 343528 (Open Web Text)

Max Activating Token Index: 43

Text #7

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6932. Min Act: -0.1700

Data Index: 2920511 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6734. Min Act: -0.1700

Data Index: 1508969 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6299. Min Act: -0.1700

Data Index: 469902 (Open Web Text)

Max Activating Token Index: 835

Text #10

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6703. Min Act: -0.1700

Data Index: 3940628 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6401. Min Act: -0.1700

Data Index: 589761 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.7016. Min Act: -0.1700

Data Index: 6369405 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6351. Min Act: -0.1700

Data Index: 4015321 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6283. Min Act: -0.1700

Data Index: 5122663 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.5715. Min Act: -0.1700

Data Index: 5431015 (Open Web Text)

Max Activating Token Index: 83

Text #16

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6146. Min Act: -0.1700

Data Index: 4569355 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.5971. Min Act: -0.1700

Data Index: 3252450 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6048. Min Act: -0.1700

Data Index: 3064288 (Open Web Text)

Max Activating Token Index: 564

Text #19

Max Range: 4.8619. Min Range: -4.8619

Max Act: 4.6095. Min Act: -0.1700

Data Index: 1239142 (Open Web Text)

Max Activating Token Index: 395