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

Dataset: Open Web Text

Neuron 1778 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: 3.6130. Min Range: -3.6130

Max Act: 3.6130. Min Act: -0.1700

Data Index: 7069184 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.6046. Min Act: -0.1700

Data Index: 3449964 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5726. Min Act: -0.1700

Data Index: 2825787 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5454. Min Act: -0.1700

Data Index: 7448044 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5744. Min Act: -0.1700

Data Index: 8055988 (Open Web Text)

Max Activating Token Index: 736

Text #5

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5673. Min Act: -0.1700

Data Index: 2875863 (Open Web Text)

Max Activating Token Index: 596

Text #6

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5315. Min Act: -0.1700

Data Index: 8241671 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5699. Min Act: -0.1700

Data Index: 8730076 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5000. Min Act: -0.1700

Data Index: 4841389 (Open Web Text)

Max Activating Token Index: 209

Text #9

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5034. Min Act: -0.1700

Data Index: 6351156 (Open Web Text)

Max Activating Token Index: 458

Text #10

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4900. Min Act: -0.1700

Data Index: 4429976 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5175. Min Act: -0.1700

Data Index: 6009822 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5071. Min Act: -0.1700

Data Index: 6070083 (Open Web Text)

Max Activating Token Index: 861

Text #13

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.5042. Min Act: -0.1700

Data Index: 7751038 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4890. Min Act: -0.1700

Data Index: 1263264 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4943. Min Act: -0.1700

Data Index: 4980353 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4988. Min Act: -0.1700

Data Index: 8147421 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4240. Min Act: -0.1700

Data Index: 6629462 (Open Web Text)

Max Activating Token Index: 993

Text #18

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4369. Min Act: -0.1700

Data Index: 4181019 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 3.6130. Min Range: -3.6130

Max Act: 3.4790. Min Act: -0.1700

Data Index: 1550603 (Open Web Text)

Max Activating Token Index: 757