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

Dataset: Open Web Text

Neuron 328 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: 3.4952. Min Range: -3.4952

Max Act: 3.4952. Min Act: -0.1700

Data Index: 5659975 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4499. Min Act: -0.1700

Data Index: 4791120 (Open Web Text)

Max Activating Token Index: 499

Text #2

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4376. Min Act: -0.1700

Data Index: 4821369 (Open Web Text)

Max Activating Token Index: 358

Text #3

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4269. Min Act: -0.1700

Data Index: 3345335 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4316. Min Act: -0.1700

Data Index: 1118667 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4272. Min Act: -0.1700

Data Index: 725715 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4365. Min Act: -0.1700

Data Index: 4419761 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4047. Min Act: -0.1700

Data Index: 4060461 (Open Web Text)

Max Activating Token Index: 355

Text #8

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4222. Min Act: -0.1700

Data Index: 5489498 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4032. Min Act: -0.1700

Data Index: 524761 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1220119 (Open Web Text)

Max Activating Token Index: 404

Text #11

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3982. Min Act: -0.1700

Data Index: 1113578 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.4085. Min Act: -0.1700

Data Index: 3487507 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3791. Min Act: -0.1700

Data Index: 2657385 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3999. Min Act: -0.1700

Data Index: 7602138 (Open Web Text)

Max Activating Token Index: 405

Text #15

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3923. Min Act: -0.1700

Data Index: 1459771 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3778. Min Act: -0.1700

Data Index: 4876679 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3879. Min Act: -0.1700

Data Index: 6587354 (Open Web Text)

Max Activating Token Index: 702

Text #18

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3650. Min Act: -0.1700

Data Index: 901986 (Open Web Text)

Max Activating Token Index: 109

Text #19

Max Range: 3.4952. Min Range: -3.4952

Max Act: 3.3665. Min Act: -0.1700

Data Index: 5566342 (Open Web Text)

Max Activating Token Index: 864