Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 3091 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8320. Min Act: -0.1700

Data Index: 7592842 (Open Web Text)

Max Activating Token Index: 72

Text #1

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 6256271 (Open Web Text)

Max Activating Token Index: 499

Text #2

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7069. Min Act: -0.1700

Data Index: 7785066 (Open Web Text)

Max Activating Token Index: 470

Text #3

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 2050318 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 3783354 (Open Web Text)

Max Activating Token Index: 216

Text #5

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 5398060 (Open Web Text)

Max Activating Token Index: 498

Text #6

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6444. Min Act: -0.1700

Data Index: 3029405 (Open Web Text)

Max Activating Token Index: 434

Text #7

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 5528717 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6757. Min Act: -0.1700

Data Index: 6718031 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6444. Min Act: -0.1700

Data Index: 5605444 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 309716 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 8739194 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 1032951 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 5829295 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 1492895 (Open Web Text)

Max Activating Token Index: 182

Text #15

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6132. Min Act: -0.1700

Data Index: 5396544 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5819. Min Act: -0.1700

Data Index: 7696032 (Open Web Text)

Max Activating Token Index: 476

Text #17

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5819. Min Act: -0.1700

Data Index: 6723810 (Open Web Text)

Max Activating Token Index: 134

Text #18

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5819. Min Act: -0.1700

Data Index: 1825882 (Open Web Text)

Max Activating Token Index: 269

Text #19

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5819. Min Act: -0.1700

Data Index: 3667412 (Open Web Text)

Max Activating Token Index: 794