Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 2100 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3077. Min Act: -0.1700

Data Index: 8733565 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3390. Min Act: -0.1700

Data Index: 2286182 (Open Web Text)

Max Activating Token Index: 948

Text #2

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3077. Min Act: -0.1700

Data Index: 879734 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3077. Min Act: -0.1700

Data Index: 3872087 (Open Web Text)

Max Activating Token Index: 251

Text #4

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3390. Min Act: -0.1700

Data Index: 5438352 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.2765. Min Act: -0.1700

Data Index: 3876520 (Open Web Text)

Max Activating Token Index: 244

Text #6

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3390. Min Act: -0.1700

Data Index: 2635889 (Open Web Text)

Max Activating Token Index: 434

Text #7

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1515. Min Act: -0.1700

Data Index: 5617940 (Open Web Text)

Max Activating Token Index: 959

Text #8

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.2452. Min Act: -0.1700

Data Index: 7900850 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.2765. Min Act: -0.1700

Data Index: 8383216 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1827. Min Act: -0.1700

Data Index: 4043371 (Open Web Text)

Max Activating Token Index: 242

Text #11

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.2140. Min Act: -0.1700

Data Index: 7076204 (Open Web Text)

Max Activating Token Index: 265

Text #12

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1827. Min Act: -0.1700

Data Index: 2672742 (Open Web Text)

Max Activating Token Index: 401

Text #13

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1827. Min Act: -0.1700

Data Index: 5797637 (Open Web Text)

Max Activating Token Index: 57

Text #14

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1202. Min Act: -0.1700

Data Index: 3480202 (Open Web Text)

Max Activating Token Index: 297

Text #15

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1515. Min Act: -0.1700

Data Index: 4322292 (Open Web Text)

Max Activating Token Index: 566

Text #16

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1202. Min Act: -0.1700

Data Index: 918221 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1202. Min Act: -0.1700

Data Index: 6465065 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1202. Min Act: -0.1700

Data Index: 1011750 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.1515. Min Act: -0.1700

Data Index: 5419724 (Open Web Text)

Max Activating Token Index: 868