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

Dataset: Open Web Text

Neuron 1250 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: 7.6094. Min Range: -7.6094

Max Act: 7.6094. Min Act: -0.1700

Data Index: 4552329 (Open Web Text)

Max Activating Token Index: 171

Text #1

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.5396. Min Act: -0.1700

Data Index: 3069249 (Open Web Text)

Max Activating Token Index: 604

Text #2

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.4879. Min Act: -0.1700

Data Index: 5351809 (Open Web Text)

Max Activating Token Index: 301

Text #3

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.3839. Min Act: -0.1700

Data Index: 7669346 (Open Web Text)

Max Activating Token Index: 792

Text #4

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.3663. Min Act: -0.1700

Data Index: 2332283 (Open Web Text)

Max Activating Token Index: 673

Text #5

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.3450. Min Act: -0.1700

Data Index: 2756813 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.3202. Min Act: -0.1700

Data Index: 4489591 (Open Web Text)

Max Activating Token Index: 403

Text #7

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.2222. Min Act: -0.1700

Data Index: 7519188 (Open Web Text)

Max Activating Token Index: 646

Text #8

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.2157. Min Act: -0.1700

Data Index: 7960330 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.2339. Min Act: -0.1700

Data Index: 6704454 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.2571. Min Act: -0.1700

Data Index: 7109071 (Open Web Text)

Max Activating Token Index: 483

Text #11

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.2422. Min Act: -0.1700

Data Index: 388318 (Open Web Text)

Max Activating Token Index: 961

Text #12

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.1942. Min Act: -0.1700

Data Index: 4647844 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.1540. Min Act: -0.1700

Data Index: 6704468 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.2014. Min Act: -0.1700

Data Index: 8551320 (Open Web Text)

Max Activating Token Index: 692

Text #15

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.2138. Min Act: -0.1700

Data Index: 3082284 (Open Web Text)

Max Activating Token Index: 139

Text #16

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.1583. Min Act: -0.1700

Data Index: 943860 (Open Web Text)

Max Activating Token Index: 876

Text #17

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.1241. Min Act: -0.1700

Data Index: 6838396 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.1619. Min Act: -0.1700

Data Index: 730444 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 7.6094. Min Range: -7.6094

Max Act: 7.0984. Min Act: -0.1700

Data Index: 4572167 (Open Web Text)

Max Activating Token Index: 381