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

Dataset: Open Web Text

Neuron 2045 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: 4.0512. Min Range: -4.0512

Max Act: 4.0076. Min Act: -0.1700

Data Index: 7718450 (Open Web Text)

Max Activating Token Index: 367

Text #1

Max Range: 4.0512. Min Range: -4.0512

Max Act: 4.0512. Min Act: -0.1700

Data Index: 2197877 (Open Web Text)

Max Activating Token Index: 843

Text #2

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.9820. Min Act: -0.1700

Data Index: 3253051 (Open Web Text)

Max Activating Token Index: 122

Text #3

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.9300. Min Act: -0.1700

Data Index: 1031958 (Open Web Text)

Max Activating Token Index: 401

Text #4

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.9015. Min Act: -0.1700

Data Index: 2069736 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.8323. Min Act: -0.1700

Data Index: 1927438 (Open Web Text)

Max Activating Token Index: 953

Text #6

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7946. Min Act: -0.1700

Data Index: 4061443 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7831. Min Act: -0.1700

Data Index: 6484442 (Open Web Text)

Max Activating Token Index: 153

Text #8

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7342. Min Act: -0.1700

Data Index: 5373084 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7562. Min Act: -0.1700

Data Index: 7282263 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7325. Min Act: -0.1700

Data Index: 2003868 (Open Web Text)

Max Activating Token Index: 710

Text #11

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7084. Min Act: -0.1700

Data Index: 8050228 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7142. Min Act: -0.1700

Data Index: 36585 (Open Web Text)

Max Activating Token Index: 336

Text #13

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7257. Min Act: -0.1700

Data Index: 2713453 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7195. Min Act: -0.1700

Data Index: 2921314 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.7214. Min Act: -0.1700

Data Index: 595202 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.6990. Min Act: -0.1700

Data Index: 3247873 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.6951. Min Act: -0.1700

Data Index: 5987632 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.6859. Min Act: -0.1700

Data Index: 3515407 (Open Web Text)

Max Activating Token Index: 167

Text #19

Max Range: 4.0512. Min Range: -4.0512

Max Act: 3.6864. Min Act: -0.1700

Data Index: 6400786 (Open Web Text)

Max Activating Token Index: 344