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

Dataset: Open Web Text

Neuron 2196 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: 3.4791. Min Range: -3.4791

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1243359 (Open Web Text)

Max Activating Token Index: 854

Text #1

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4618. Min Act: -0.1700

Data Index: 6571140 (Open Web Text)

Max Activating Token Index: 196

Text #2

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4391. Min Act: -0.1700

Data Index: 7828370 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4321. Min Act: -0.1700

Data Index: 6061367 (Open Web Text)

Max Activating Token Index: 575

Text #4

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4279. Min Act: -0.1700

Data Index: 974274 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4130. Min Act: -0.1700

Data Index: 7005781 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4167. Min Act: -0.1700

Data Index: 2441002 (Open Web Text)

Max Activating Token Index: 204

Text #7

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.4141. Min Act: -0.1700

Data Index: 4627208 (Open Web Text)

Max Activating Token Index: 191

Text #8

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3953. Min Act: -0.1700

Data Index: 6571131 (Open Web Text)

Max Activating Token Index: 764

Text #9

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3950. Min Act: -0.1700

Data Index: 2638049 (Open Web Text)

Max Activating Token Index: 642

Text #10

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3854. Min Act: -0.1700

Data Index: 5407132 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3729. Min Act: -0.1700

Data Index: 8453011 (Open Web Text)

Max Activating Token Index: 280

Text #12

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3794. Min Act: -0.1700

Data Index: 6508932 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3764. Min Act: -0.1700

Data Index: 6645950 (Open Web Text)

Max Activating Token Index: 753

Text #14

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3725. Min Act: -0.1700

Data Index: 6487487 (Open Web Text)

Max Activating Token Index: 977

Text #15

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3843. Min Act: -0.1700

Data Index: 432597 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3794. Min Act: -0.1700

Data Index: 8000225 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3604. Min Act: -0.1700

Data Index: 4622864 (Open Web Text)

Max Activating Token Index: 871

Text #18

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3571. Min Act: -0.1700

Data Index: 3123312 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 3.4791. Min Range: -3.4791

Max Act: 3.3406. Min Act: -0.1700

Data Index: 1153965 (Open Web Text)

Max Activating Token Index: 275