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

Dataset: Open Web Text

Neuron 1409 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: 4.1124. Min Range: -4.1124

Max Act: 4.1124. Min Act: -0.1700

Data Index: 2295956 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 4.1124. Min Range: -4.1124

Max Act: 4.0273. Min Act: -0.1700

Data Index: 6320615 (Open Web Text)

Max Activating Token Index: 280

Text #2

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.9839. Min Act: -0.1700

Data Index: 1457906 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.9876. Min Act: -0.1700

Data Index: 4808183 (Open Web Text)

Max Activating Token Index: 980

Text #4

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.9476. Min Act: -0.1700

Data Index: 7888441 (Open Web Text)

Max Activating Token Index: 177

Text #5

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.9363. Min Act: -0.1700

Data Index: 4458758 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.9075. Min Act: -0.1700

Data Index: 4137832 (Open Web Text)

Max Activating Token Index: 460

Text #7

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.9433. Min Act: -0.1700

Data Index: 2013871 (Open Web Text)

Max Activating Token Index: 319

Text #8

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.9232. Min Act: -0.1700

Data Index: 1384327 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8806. Min Act: -0.1700

Data Index: 2166546 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8749. Min Act: -0.1700

Data Index: 2236671 (Open Web Text)

Max Activating Token Index: 579

Text #11

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8527. Min Act: -0.1700

Data Index: 6340004 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8705. Min Act: -0.1700

Data Index: 5209785 (Open Web Text)

Max Activating Token Index: 747

Text #13

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8736. Min Act: -0.1700

Data Index: 6305035 (Open Web Text)

Max Activating Token Index: 669

Text #14

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8630. Min Act: -0.1700

Data Index: 3200687 (Open Web Text)

Max Activating Token Index: 749

Text #15

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8620. Min Act: -0.1700

Data Index: 94347 (Open Web Text)

Max Activating Token Index: 238

Text #16

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8232. Min Act: -0.1700

Data Index: 4779864 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8476. Min Act: -0.1700

Data Index: 4658332 (Open Web Text)

Max Activating Token Index: 90

Text #18

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8357. Min Act: -0.1700

Data Index: 2486199 (Open Web Text)

Max Activating Token Index: 247

Text #19

Max Range: 4.1124. Min Range: -4.1124

Max Act: 3.8189. Min Act: -0.1700

Data Index: 6261462 (Open Web Text)

Max Activating Token Index: 209