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

Dataset: Open Web Text

Neuron 1807 in Layer 3

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: 4.6857. Min Range: -4.6857

Max Act: 4.6810. Min Act: -0.1700

Data Index: 7693378 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.6857. Min Act: -0.1700

Data Index: 2444761 (Open Web Text)

Max Activating Token Index: 969

Text #2

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.6005. Min Act: -0.1700

Data Index: 5094259 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.6248. Min Act: -0.1700

Data Index: 3589750 (Open Web Text)

Max Activating Token Index: 625

Text #4

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.4938. Min Act: -0.1700

Data Index: 6479364 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.4964. Min Act: -0.1700

Data Index: 3804680 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.4373. Min Act: -0.1700

Data Index: 4127216 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.3507. Min Act: -0.1700

Data Index: 5502768 (Open Web Text)

Max Activating Token Index: 447

Text #8

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.3297. Min Act: -0.1700

Data Index: 221634 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.3065. Min Act: -0.1700

Data Index: 2243623 (Open Web Text)

Max Activating Token Index: 46

Text #10

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.1815. Min Act: -0.1700

Data Index: 679137 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.2293. Min Act: -0.1700

Data Index: 7393315 (Open Web Text)

Max Activating Token Index: 907

Text #12

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.1367. Min Act: -0.1700

Data Index: 2182932 (Open Web Text)

Max Activating Token Index: 774

Text #13

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.0489. Min Act: -0.1700

Data Index: 5357142 (Open Web Text)

Max Activating Token Index: 954

Text #14

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.1005. Min Act: -0.1700

Data Index: 3831234 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.0733. Min Act: -0.1700

Data Index: 7260335 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.0716. Min Act: -0.1700

Data Index: 2507177 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.0365. Min Act: -0.1700

Data Index: 5872127 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.0332. Min Act: -0.1700

Data Index: 726694 (Open Web Text)

Max Activating Token Index: 468

Text #19

Max Range: 4.6857. Min Range: -4.6857

Max Act: 4.0167. Min Act: -0.1700

Data Index: 3313026 (Open Web Text)

Max Activating Token Index: 383