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

Dataset: Open Web Text

Neuron 2435 in Layer 1

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: 4.5992. Min Range: -4.5992

Max Act: 4.5992. Min Act: -0.1700

Data Index: 2928983 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.5382. Min Act: -0.1700

Data Index: 8610598 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4696. Min Act: -0.1700

Data Index: 4877865 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4523. Min Act: -0.1700

Data Index: 8610593 (Open Web Text)

Max Activating Token Index: 878

Text #4

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4606. Min Act: -0.1700

Data Index: 942986 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4675. Min Act: -0.1700

Data Index: 6116091 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4612. Min Act: -0.1700

Data Index: 7142136 (Open Web Text)

Max Activating Token Index: 518

Text #7

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4500. Min Act: -0.1700

Data Index: 6326103 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4278. Min Act: -0.1700

Data Index: 3048566 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4231. Min Act: -0.1700

Data Index: 394289 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3968. Min Act: -0.1700

Data Index: 384153 (Open Web Text)

Max Activating Token Index: 439

Text #11

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3800. Min Act: -0.1700

Data Index: 7506632 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4048. Min Act: -0.1700

Data Index: 3310515 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.4072. Min Act: -0.1700

Data Index: 5921670 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3693. Min Act: -0.1700

Data Index: 7329286 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3767. Min Act: -0.1700

Data Index: 1146402 (Open Web Text)

Max Activating Token Index: 240

Text #16

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3755. Min Act: -0.1700

Data Index: 989787 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3575. Min Act: -0.1700

Data Index: 343217 (Open Web Text)

Max Activating Token Index: 453

Text #18

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3507. Min Act: -0.1700

Data Index: 967372 (Open Web Text)

Max Activating Token Index: 77

Text #19

Max Range: 4.5992. Min Range: -4.5992

Max Act: 4.3680. Min Act: -0.1700

Data Index: 3045773 (Open Web Text)

Max Activating Token Index: 575