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

Dataset: Open Web Text

Neuron 2500 in Layer 6

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: 5.5814. Min Range: -5.5814

Max Act: 5.5814. Min Act: -0.1700

Data Index: 5246543 (Open Web Text)

Max Activating Token Index: 287

Text #1

Max Range: 5.5814. Min Range: -5.5814

Max Act: 5.2818. Min Act: -0.1700

Data Index: 7598248 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 5.5814. Min Range: -5.5814

Max Act: 5.2469. Min Act: -0.1700

Data Index: 4112314 (Open Web Text)

Max Activating Token Index: 607

Text #3

Max Range: 5.5814. Min Range: -5.5814

Max Act: 5.1923. Min Act: -0.1700

Data Index: 6041652 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 5.5814. Min Range: -5.5814

Max Act: 5.1180. Min Act: -0.1700

Data Index: 39323 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9763. Min Act: -0.1700

Data Index: 296800 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9840. Min Act: -0.1700

Data Index: 7995297 (Open Web Text)

Max Activating Token Index: 284

Text #7

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9377. Min Act: -0.1700

Data Index: 2083098 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9357. Min Act: -0.1700

Data Index: 2357500 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9206. Min Act: -0.1700

Data Index: 6912970 (Open Web Text)

Max Activating Token Index: 840

Text #10

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9146. Min Act: -0.1700

Data Index: 7635518 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9054. Min Act: -0.1700

Data Index: 1105669 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9108. Min Act: -0.1700

Data Index: 8345344 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.9119. Min Act: -0.1700

Data Index: 1825205 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.8583. Min Act: -0.1700

Data Index: 2105535 (Open Web Text)

Max Activating Token Index: 209

Text #15

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.8526. Min Act: -0.1700

Data Index: 2736646 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.8675. Min Act: -0.1700

Data Index: 4621018 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.8441. Min Act: -0.1700

Data Index: 4316825 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.8471. Min Act: -0.1700

Data Index: 8256005 (Open Web Text)

Max Activating Token Index: 266

Text #19

Max Range: 5.5814. Min Range: -5.5814

Max Act: 4.8451. Min Act: -0.1700

Data Index: 66826 (Open Web Text)

Max Activating Token Index: 346