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

Dataset: Open Web Text

Neuron 843 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: 4.5319. Min Range: -4.5319

Max Act: 4.5319. Min Act: -0.1700

Data Index: 5392191 (Open Web Text)

Max Activating Token Index: 53

Text #1

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4606. Min Act: -0.1700

Data Index: 8655855 (Open Web Text)

Max Activating Token Index: 202

Text #2

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4407. Min Act: -0.1700

Data Index: 454928 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4348. Min Act: -0.1700

Data Index: 2441716 (Open Web Text)

Max Activating Token Index: 277

Text #4

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4014. Min Act: -0.1700

Data Index: 4875542 (Open Web Text)

Max Activating Token Index: 387

Text #5

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4410. Min Act: -0.1700

Data Index: 3761767 (Open Web Text)

Max Activating Token Index: 184

Text #6

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4284. Min Act: -0.1700

Data Index: 3632164 (Open Web Text)

Max Activating Token Index: 365

Text #7

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4220. Min Act: -0.1700

Data Index: 1254994 (Open Web Text)

Max Activating Token Index: 412

Text #8

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3833. Min Act: -0.1700

Data Index: 4879972 (Open Web Text)

Max Activating Token Index: 438

Text #9

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3790. Min Act: -0.1700

Data Index: 7315270 (Open Web Text)

Max Activating Token Index: 124

Text #10

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4190. Min Act: -0.1700

Data Index: 5732212 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3889. Min Act: -0.1700

Data Index: 1508661 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4308. Min Act: -0.1700

Data Index: 4879970 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4103. Min Act: -0.1700

Data Index: 6972699 (Open Web Text)

Max Activating Token Index: 501

Text #14

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3780. Min Act: -0.1700

Data Index: 7399597 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3685. Min Act: -0.1700

Data Index: 7609843 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4171. Min Act: -0.1700

Data Index: 8242098 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4056. Min Act: -0.1700

Data Index: 6078842 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.3782. Min Act: -0.1700

Data Index: 8567666 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 4.5319. Min Range: -4.5319

Max Act: 4.4165. Min Act: -0.1700

Data Index: 1119938 (Open Web Text)

Max Activating Token Index: 94