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

Dataset: Open Web Text

Neuron 342 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: 3.6261. Min Range: -3.6261

Max Act: 3.6139. Min Act: -0.1700

Data Index: 5046903 (Open Web Text)

Max Activating Token Index: 297

Text #1

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.6261. Min Act: -0.1700

Data Index: 682807 (Open Web Text)

Max Activating Token Index: 270

Text #2

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.5880. Min Act: -0.1700

Data Index: 3057352 (Open Web Text)

Max Activating Token Index: 786

Text #3

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.5661. Min Act: -0.1700

Data Index: 3697457 (Open Web Text)

Max Activating Token Index: 120

Text #4

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.5298. Min Act: -0.1700

Data Index: 491182 (Open Web Text)

Max Activating Token Index: 853

Text #5

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.5334. Min Act: -0.1700

Data Index: 8713267 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.5254. Min Act: -0.1700

Data Index: 7597050 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4957. Min Act: -0.1700

Data Index: 2312307 (Open Web Text)

Max Activating Token Index: 220

Text #8

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4967. Min Act: -0.1700

Data Index: 4404901 (Open Web Text)

Max Activating Token Index: 917

Text #9

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4790. Min Act: -0.1700

Data Index: 788339 (Open Web Text)

Max Activating Token Index: 99

Text #10

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4429. Min Act: -0.1700

Data Index: 4981294 (Open Web Text)

Max Activating Token Index: 916

Text #11

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4865. Min Act: -0.1700

Data Index: 2460865 (Open Web Text)

Max Activating Token Index: 730

Text #12

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4773. Min Act: -0.1700

Data Index: 3748224 (Open Web Text)

Max Activating Token Index: 533

Text #13

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4596. Min Act: -0.1700

Data Index: 3491815 (Open Web Text)

Max Activating Token Index: 40

Text #14

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4426. Min Act: -0.1700

Data Index: 3004805 (Open Web Text)

Max Activating Token Index: 881

Text #15

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4388. Min Act: -0.1700

Data Index: 3697456 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4200. Min Act: -0.1700

Data Index: 4469142 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4296. Min Act: -0.1700

Data Index: 7644812 (Open Web Text)

Max Activating Token Index: 377

Text #18

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4268. Min Act: -0.1700

Data Index: 2539000 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 3.6261. Min Range: -3.6261

Max Act: 3.4101. Min Act: -0.1700

Data Index: 7175052 (Open Web Text)

Max Activating Token Index: 1021