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

Dataset: Open Web Text

Neuron 1894 in Layer 0

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: 3.6553. Min Range: -3.6553

Max Act: 3.6553. Min Act: -0.1700

Data Index: 3577423 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5984. Min Act: -0.1700

Data Index: 5869742 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5869. Min Act: -0.1700

Data Index: 5033473 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5654. Min Act: -0.1700

Data Index: 4079413 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5078. Min Act: -0.1700

Data Index: 669529 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1265491 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5030. Min Act: -0.1700

Data Index: 3995759 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5150. Min Act: -0.1700

Data Index: 8466063 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5112. Min Act: -0.1700

Data Index: 3896362 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5104. Min Act: -0.1700

Data Index: 1941285 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5219. Min Act: -0.1700

Data Index: 546495 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5104. Min Act: -0.1700

Data Index: 7355469 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5053. Min Act: -0.1700

Data Index: 4259714 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.5177. Min Act: -0.1700

Data Index: 2004058 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.4800. Min Act: -0.1700

Data Index: 7979029 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.4903. Min Act: -0.1700

Data Index: 6201346 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.4762. Min Act: -0.1700

Data Index: 4800515 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.4790. Min Act: -0.1700

Data Index: 1715010 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.4690. Min Act: -0.1700

Data Index: 944675 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6553. Min Range: -3.6553

Max Act: 3.4498. Min Act: -0.1700

Data Index: 3995761 (Open Web Text)

Max Activating Token Index: 7