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

Dataset: Open Web Text

Neuron 1399 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: 3.7887. Min Range: -3.7887

Max Act: 3.7887. Min Act: -0.1700

Data Index: 3474763 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.7362. Min Act: -0.1700

Data Index: 3114162 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.6197. Min Act: -0.1700

Data Index: 1680134 (Open Web Text)

Max Activating Token Index: 600

Text #3

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.6467. Min Act: -0.1700

Data Index: 1876094 (Open Web Text)

Max Activating Token Index: 303

Text #4

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5984. Min Act: -0.1700

Data Index: 6821790 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5990. Min Act: -0.1700

Data Index: 8142233 (Open Web Text)

Max Activating Token Index: 118

Text #6

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5866. Min Act: -0.1700

Data Index: 282183 (Open Web Text)

Max Activating Token Index: 215

Text #7

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5732. Min Act: -0.1700

Data Index: 4258692 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5486. Min Act: -0.1700

Data Index: 7493917 (Open Web Text)

Max Activating Token Index: 861

Text #9

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5637. Min Act: -0.1700

Data Index: 5416967 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5786. Min Act: -0.1700

Data Index: 3667311 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5539. Min Act: -0.1700

Data Index: 7908707 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5490. Min Act: -0.1700

Data Index: 6381716 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5646. Min Act: -0.1700

Data Index: 3701223 (Open Web Text)

Max Activating Token Index: 531

Text #14

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5328. Min Act: -0.1700

Data Index: 3498396 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5409. Min Act: -0.1700

Data Index: 7444458 (Open Web Text)

Max Activating Token Index: 925

Text #16

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5339. Min Act: -0.1700

Data Index: 6086301 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5280. Min Act: -0.1700

Data Index: 5155853 (Open Web Text)

Max Activating Token Index: 33

Text #18

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5063. Min Act: -0.1700

Data Index: 3249618 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 3.7887. Min Range: -3.7887

Max Act: 3.5111. Min Act: -0.1700

Data Index: 6636559 (Open Web Text)

Max Activating Token Index: 481