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

Dataset: Open Web Text

Neuron 638 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: 3.9255. Min Range: -3.9255

Max Act: 3.9255. Min Act: -0.1700

Data Index: 4241979 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.8399. Min Act: -0.1700

Data Index: 7144745 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7636. Min Act: -0.1700

Data Index: 3341903 (Open Web Text)

Max Activating Token Index: 369

Text #3

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7273. Min Act: -0.1700

Data Index: 1444783 (Open Web Text)

Max Activating Token Index: 1018

Text #4

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7272. Min Act: -0.1700

Data Index: 2126605 (Open Web Text)

Max Activating Token Index: 280

Text #5

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7886. Min Act: -0.1700

Data Index: 7084115 (Open Web Text)

Max Activating Token Index: 333

Text #6

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7141. Min Act: -0.1700

Data Index: 1651235 (Open Web Text)

Max Activating Token Index: 143

Text #7

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7284. Min Act: -0.1700

Data Index: 6263823 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7280. Min Act: -0.1700

Data Index: 5633131 (Open Web Text)

Max Activating Token Index: 781

Text #9

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7436. Min Act: -0.1700

Data Index: 2927438 (Open Web Text)

Max Activating Token Index: 745

Text #10

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7272. Min Act: -0.1700

Data Index: 5101493 (Open Web Text)

Max Activating Token Index: 847

Text #11

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7233. Min Act: -0.1700

Data Index: 7573078 (Open Web Text)

Max Activating Token Index: 872

Text #12

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1309476 (Open Web Text)

Max Activating Token Index: 579

Text #13

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7157. Min Act: -0.1700

Data Index: 3978213 (Open Web Text)

Max Activating Token Index: 612

Text #14

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7041. Min Act: -0.1700

Data Index: 3707121 (Open Web Text)

Max Activating Token Index: 181

Text #15

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.7530. Min Act: -0.1700

Data Index: 4454071 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.6920. Min Act: -0.1700

Data Index: 4582086 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.6485. Min Act: -0.1700

Data Index: 2150129 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.6451. Min Act: -0.1700

Data Index: 40066 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 3.9255. Min Range: -3.9255

Max Act: 3.6584. Min Act: -0.1700

Data Index: 2444816 (Open Web Text)

Max Activating Token Index: 79