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

Dataset: Open Web Text

Neuron 218 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: 4.0814. Min Range: -4.0814

Max Act: 4.0814. Min Act: -0.1700

Data Index: 1180295 (Open Web Text)

Max Activating Token Index: 828

Text #1

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.8548. Min Act: -0.1700

Data Index: 7284195 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.8170. Min Act: -0.1700

Data Index: 7237154 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.7855. Min Act: -0.1700

Data Index: 1501498 (Open Web Text)

Max Activating Token Index: 744

Text #4

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.7847. Min Act: -0.1700

Data Index: 6008819 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.7278. Min Act: -0.1700

Data Index: 3439788 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6906. Min Act: -0.1700

Data Index: 8208053 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6819. Min Act: -0.1700

Data Index: 8479878 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6614. Min Act: -0.1700

Data Index: 6280597 (Open Web Text)

Max Activating Token Index: 998

Text #9

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6822. Min Act: -0.1700

Data Index: 6037610 (Open Web Text)

Max Activating Token Index: 855

Text #10

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6344. Min Act: -0.1700

Data Index: 4899725 (Open Web Text)

Max Activating Token Index: 966

Text #11

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6601. Min Act: -0.1700

Data Index: 3293304 (Open Web Text)

Max Activating Token Index: 552

Text #12

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6215. Min Act: -0.1700

Data Index: 5604850 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6411. Min Act: -0.1700

Data Index: 6111642 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6432. Min Act: -0.1700

Data Index: 4718484 (Open Web Text)

Max Activating Token Index: 499

Text #15

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.5837. Min Act: -0.1700

Data Index: 7005317 (Open Web Text)

Max Activating Token Index: 305

Text #16

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.5689. Min Act: -0.1700

Data Index: 3580400 (Open Web Text)

Max Activating Token Index: 270

Text #17

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.6031. Min Act: -0.1700

Data Index: 3952876 (Open Web Text)

Max Activating Token Index: 229

Text #18

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.5979. Min Act: -0.1700

Data Index: 3952878 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 4.0814. Min Range: -4.0814

Max Act: 3.5935. Min Act: -0.1700

Data Index: 5942065 (Open Web Text)

Max Activating Token Index: 214