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

Dataset: Open Web Text

Neuron 497 in Layer 2

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: 3.5435. Min Range: -3.5435

Max Act: 3.5434. Min Act: -0.1700

Data Index: 524918 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.5435. Min Act: -0.1700

Data Index: 6376019 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.5185. Min Act: -0.1700

Data Index: 335464 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.5050. Min Act: -0.1700

Data Index: 4135534 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4960. Min Act: -0.1700

Data Index: 836334 (Open Web Text)

Max Activating Token Index: 307

Text #5

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4916. Min Act: -0.1700

Data Index: 5780320 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4800. Min Act: -0.1700

Data Index: 1850246 (Open Web Text)

Max Activating Token Index: 400

Text #7

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4616. Min Act: -0.1700

Data Index: 3020954 (Open Web Text)

Max Activating Token Index: 413

Text #8

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4616. Min Act: -0.1700

Data Index: 4459383 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4655. Min Act: -0.1700

Data Index: 5353871 (Open Web Text)

Max Activating Token Index: 189

Text #10

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4584. Min Act: -0.1700

Data Index: 6415430 (Open Web Text)

Max Activating Token Index: 924

Text #11

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4617. Min Act: -0.1700

Data Index: 1448061 (Open Web Text)

Max Activating Token Index: 53

Text #12

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4582. Min Act: -0.1700

Data Index: 4353205 (Open Web Text)

Max Activating Token Index: 622

Text #13

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4630. Min Act: -0.1700

Data Index: 6518315 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1162335 (Open Web Text)

Max Activating Token Index: 50

Text #15

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4164. Min Act: -0.1700

Data Index: 4881742 (Open Web Text)

Max Activating Token Index: 911

Text #16

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.3999. Min Act: -0.1700

Data Index: 49730 (Open Web Text)

Max Activating Token Index: 985

Text #17

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.3925. Min Act: -0.1700

Data Index: 2325411 (Open Web Text)

Max Activating Token Index: 69

Text #18

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.4016. Min Act: -0.1700

Data Index: 6362124 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 3.5435. Min Range: -3.5435

Max Act: 3.3928. Min Act: -0.1700

Data Index: 6392626 (Open Web Text)

Max Activating Token Index: 74