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

Dataset: Open Web Text

Neuron 190 in Layer 2

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: 4.6920. Min Range: -4.6920

Max Act: 4.6919. Min Act: -0.1700

Data Index: 5683239 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6920. Min Act: -0.1700

Data Index: 5902210 (Open Web Text)

Max Activating Token Index: 486

Text #2

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6714. Min Act: -0.1700

Data Index: 8193415 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6733. Min Act: -0.1700

Data Index: 2569396 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6107. Min Act: -0.1700

Data Index: 822955 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6415. Min Act: -0.1700

Data Index: 2107843 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6509. Min Act: -0.1700

Data Index: 3141055 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5895. Min Act: -0.1700

Data Index: 3854274 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5894. Min Act: -0.1700

Data Index: 3153026 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6281. Min Act: -0.1700

Data Index: 5336164 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6465. Min Act: -0.1700

Data Index: 8056385 (Open Web Text)

Max Activating Token Index: 230

Text #11

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5956. Min Act: -0.1700

Data Index: 6859051 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5891. Min Act: -0.1700

Data Index: 1767510 (Open Web Text)

Max Activating Token Index: 482

Text #13

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5911. Min Act: -0.1700

Data Index: 5270153 (Open Web Text)

Max Activating Token Index: 504

Text #14

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6203. Min Act: -0.1700

Data Index: 4823877 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5678. Min Act: -0.1700

Data Index: 2952230 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5865. Min Act: -0.1700

Data Index: 3166805 (Open Web Text)

Max Activating Token Index: 460

Text #17

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5731. Min Act: -0.1700

Data Index: 5424939 (Open Web Text)

Max Activating Token Index: 403

Text #18

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.5659. Min Act: -0.1700

Data Index: 1427451 (Open Web Text)

Max Activating Token Index: 657

Text #19

Max Range: 4.6920. Min Range: -4.6920

Max Act: 4.6382. Min Act: -0.1700

Data Index: 3406057 (Open Web Text)

Max Activating Token Index: 336