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

Dataset: Open Web Text

Neuron 1448 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: 2.5979. Min Range: -2.5979

Max Act: 2.5979. Min Act: -0.1700

Data Index: 1486154 (Open Web Text)

Max Activating Token Index: 761

Text #1

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5912. Min Act: -0.1700

Data Index: 8633548 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5744. Min Act: -0.1700

Data Index: 3653885 (Open Web Text)

Max Activating Token Index: 168

Text #3

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5828. Min Act: -0.1700

Data Index: 1456664 (Open Web Text)

Max Activating Token Index: 296

Text #4

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5671. Min Act: -0.1700

Data Index: 2611174 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5873. Min Act: -0.1700

Data Index: 8385197 (Open Web Text)

Max Activating Token Index: 649

Text #6

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5775. Min Act: -0.1700

Data Index: 2928036 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5570. Min Act: -0.1700

Data Index: 3111067 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5490. Min Act: -0.1700

Data Index: 8564394 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5449. Min Act: -0.1700

Data Index: 4311989 (Open Web Text)

Max Activating Token Index: 160

Text #10

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5519. Min Act: -0.1700

Data Index: 2806310 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5329. Min Act: -0.1700

Data Index: 8445642 (Open Web Text)

Max Activating Token Index: 792

Text #12

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5582. Min Act: -0.1700

Data Index: 8606254 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5205. Min Act: -0.1700

Data Index: 4076146 (Open Web Text)

Max Activating Token Index: 681

Text #14

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5277. Min Act: -0.1700

Data Index: 550074 (Open Web Text)

Max Activating Token Index: 938

Text #15

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5349. Min Act: -0.1700

Data Index: 699648 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5349. Min Act: -0.1700

Data Index: 6409804 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5098. Min Act: -0.1700

Data Index: 2455461 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5190. Min Act: -0.1700

Data Index: 2616436 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 2.5979. Min Range: -2.5979

Max Act: 2.5095. Min Act: -0.1700

Data Index: 2622159 (Open Web Text)

Max Activating Token Index: 64