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

Dataset: Open Web Text

Neuron 725 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: 1.7376. Min Range: -1.7376

Max Act: 1.7376. Min Act: -0.1700

Data Index: 5793275 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.7079. Min Act: -0.1700

Data Index: 2276232 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6657. Min Act: -0.1700

Data Index: 2810668 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6322. Min Act: -0.1700

Data Index: 6412482 (Open Web Text)

Max Activating Token Index: 276

Text #4

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6209. Min Act: -0.1700

Data Index: 2310787 (Open Web Text)

Max Activating Token Index: 782

Text #5

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6107. Min Act: -0.1700

Data Index: 3575609 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6174. Min Act: -0.1700

Data Index: 412554 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6152. Min Act: -0.1700

Data Index: 2231736 (Open Web Text)

Max Activating Token Index: 958

Text #8

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6125. Min Act: -0.1700

Data Index: 4550504 (Open Web Text)

Max Activating Token Index: 876

Text #9

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6055. Min Act: -0.1700

Data Index: 604796 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6089. Min Act: -0.1700

Data Index: 4191669 (Open Web Text)

Max Activating Token Index: 159

Text #11

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6093. Min Act: -0.1700

Data Index: 2999097 (Open Web Text)

Max Activating Token Index: 791

Text #12

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.5943. Min Act: -0.1700

Data Index: 1298099 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.5940. Min Act: -0.1700

Data Index: 309983 (Open Web Text)

Max Activating Token Index: 569

Text #14

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.6001. Min Act: -0.1700

Data Index: 5715756 (Open Web Text)

Max Activating Token Index: 718

Text #15

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.5994. Min Act: -0.1700

Data Index: 3177936 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.5984. Min Act: -0.1700

Data Index: 1671591 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.5987. Min Act: -0.1700

Data Index: 4074776 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.5847. Min Act: -0.1700

Data Index: 6298837 (Open Web Text)

Max Activating Token Index: 68

Text #19

Max Range: 1.7376. Min Range: -1.7376

Max Act: 1.5915. Min Act: -0.1700

Data Index: 6528146 (Open Web Text)

Max Activating Token Index: 166