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

Dataset: Open Web Text

Neuron 875 in Layer 2

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: 4.7997. Min Range: -4.7997

Max Act: 4.7997. Min Act: -0.1700

Data Index: 7488914 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7839. Min Act: -0.1700

Data Index: 1090000 (Open Web Text)

Max Activating Token Index: 1002

Text #2

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7689. Min Act: -0.1700

Data Index: 8179827 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7110. Min Act: -0.1700

Data Index: 6415798 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6974. Min Act: -0.1700

Data Index: 912715 (Open Web Text)

Max Activating Token Index: 910

Text #5

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7061. Min Act: -0.1700

Data Index: 8626928 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6835. Min Act: -0.1700

Data Index: 4769609 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6999. Min Act: -0.1700

Data Index: 7407628 (Open Web Text)

Max Activating Token Index: 218

Text #8

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6998. Min Act: -0.1700

Data Index: 2220470 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6258. Min Act: -0.1700

Data Index: 60152 (Open Web Text)

Max Activating Token Index: 874

Text #10

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6461. Min Act: -0.1700

Data Index: 2428298 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6566. Min Act: -0.1700

Data Index: 5310899 (Open Web Text)

Max Activating Token Index: 115

Text #12

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6315. Min Act: -0.1700

Data Index: 4819533 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6252. Min Act: -0.1700

Data Index: 7435940 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6056. Min Act: -0.1700

Data Index: 6175809 (Open Web Text)

Max Activating Token Index: 933

Text #15

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6265. Min Act: -0.1700

Data Index: 1801988 (Open Web Text)

Max Activating Token Index: 231

Text #16

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6220. Min Act: -0.1700

Data Index: 3979457 (Open Web Text)

Max Activating Token Index: 380

Text #17

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5680. Min Act: -0.1700

Data Index: 1577670 (Open Web Text)

Max Activating Token Index: 171

Text #18

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5800. Min Act: -0.1700

Data Index: 6402336 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5948. Min Act: -0.1700

Data Index: 2287205 (Open Web Text)

Max Activating Token Index: 317