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

Dataset: Open Web Text

Neuron 568 in Layer 3

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: 4.8844. Min Range: -4.8844

Max Act: 4.8844. Min Act: -0.1700

Data Index: 1306580 (Open Web Text)

Max Activating Token Index: 176

Text #1

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.7866. Min Act: -0.1700

Data Index: 7848324 (Open Web Text)

Max Activating Token Index: 805

Text #2

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.7435. Min Act: -0.1700

Data Index: 6169429 (Open Web Text)

Max Activating Token Index: 586

Text #3

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.6722. Min Act: -0.1700

Data Index: 5303041 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.6124. Min Act: -0.1700

Data Index: 8483915 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.6316. Min Act: -0.1700

Data Index: 8397402 (Open Web Text)

Max Activating Token Index: 59

Text #6

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.6167. Min Act: -0.1700

Data Index: 3051267 (Open Web Text)

Max Activating Token Index: 112

Text #7

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.6052. Min Act: -0.1700

Data Index: 5850903 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5884. Min Act: -0.1700

Data Index: 2259397 (Open Web Text)

Max Activating Token Index: 317

Text #9

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.6263. Min Act: -0.1700

Data Index: 5670433 (Open Web Text)

Max Activating Token Index: 56

Text #10

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.6014. Min Act: -0.1700

Data Index: 1256425 (Open Web Text)

Max Activating Token Index: 359

Text #11

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5977. Min Act: -0.1700

Data Index: 6162949 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5761. Min Act: -0.1700

Data Index: 6706108 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5442. Min Act: -0.1700

Data Index: 6459255 (Open Web Text)

Max Activating Token Index: 529

Text #14

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5759. Min Act: -0.1700

Data Index: 2720832 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5702. Min Act: -0.1700

Data Index: 8537878 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5560. Min Act: -0.1700

Data Index: 8140310 (Open Web Text)

Max Activating Token Index: 330

Text #17

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5265. Min Act: -0.1700

Data Index: 6919131 (Open Web Text)

Max Activating Token Index: 202

Text #18

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5431. Min Act: -0.1700

Data Index: 3291089 (Open Web Text)

Max Activating Token Index: 727

Text #19

Max Range: 4.8844. Min Range: -4.8844

Max Act: 4.5662. Min Act: -0.1700

Data Index: 4531328 (Open Web Text)

Max Activating Token Index: 322