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

Dataset: Open Web Text

Neuron 2194 in Layer 5

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: 4.3435. Min Range: -4.3435

Max Act: 4.3435. Min Act: -0.1700

Data Index: 2602306 (Open Web Text)

Max Activating Token Index: 764

Text #1

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.3076. Min Act: -0.1700

Data Index: 5784116 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.3001. Min Act: -0.1700

Data Index: 2524467 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2862. Min Act: -0.1700

Data Index: 2851365 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2351. Min Act: -0.1700

Data Index: 7158034 (Open Web Text)

Max Activating Token Index: 880

Text #5

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.3004. Min Act: -0.1700

Data Index: 7318016 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2757. Min Act: -0.1700

Data Index: 1505224 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2673. Min Act: -0.1700

Data Index: 71018 (Open Web Text)

Max Activating Token Index: 798

Text #8

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2082. Min Act: -0.1700

Data Index: 3976891 (Open Web Text)

Max Activating Token Index: 948

Text #9

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2630. Min Act: -0.1700

Data Index: 6587151 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2049. Min Act: -0.1700

Data Index: 2893187 (Open Web Text)

Max Activating Token Index: 188

Text #11

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1987. Min Act: -0.1700

Data Index: 1934431 (Open Web Text)

Max Activating Token Index: 275

Text #12

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.2198. Min Act: -0.1700

Data Index: 1093325 (Open Web Text)

Max Activating Token Index: 397

Text #13

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1959. Min Act: -0.1700

Data Index: 3179697 (Open Web Text)

Max Activating Token Index: 562

Text #14

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1923. Min Act: -0.1700

Data Index: 3008876 (Open Web Text)

Max Activating Token Index: 307

Text #15

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1941. Min Act: -0.1700

Data Index: 3094452 (Open Web Text)

Max Activating Token Index: 995

Text #16

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1493. Min Act: -0.1700

Data Index: 5955994 (Open Web Text)

Max Activating Token Index: 193

Text #17

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1781. Min Act: -0.1700

Data Index: 6418409 (Open Web Text)

Max Activating Token Index: 318

Text #18

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1277. Min Act: -0.1700

Data Index: 2755397 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 4.3435. Min Range: -4.3435

Max Act: 4.1399. Min Act: -0.1700

Data Index: 6522925 (Open Web Text)

Max Activating Token Index: 452