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

Dataset: Open Web Text

Neuron 2746 in Layer 4

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: 3.2865. Min Range: -3.2865

Max Act: 3.2865. Min Act: -0.1700

Data Index: 2385865 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2677. Min Act: -0.1700

Data Index: 5586464 (Open Web Text)

Max Activating Token Index: 592

Text #2

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2655. Min Act: -0.1700

Data Index: 2112363 (Open Web Text)

Max Activating Token Index: 173

Text #3

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2440. Min Act: -0.1700

Data Index: 1955938 (Open Web Text)

Max Activating Token Index: 229

Text #4

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2197. Min Act: -0.1700

Data Index: 5454705 (Open Web Text)

Max Activating Token Index: 1009

Text #5

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2237. Min Act: -0.1700

Data Index: 4882879 (Open Web Text)

Max Activating Token Index: 795

Text #6

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2506. Min Act: -0.1700

Data Index: 7908345 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2718. Min Act: -0.1700

Data Index: 1925949 (Open Web Text)

Max Activating Token Index: 648

Text #8

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2738. Min Act: -0.1700

Data Index: 474255 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2383. Min Act: -0.1700

Data Index: 6412317 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2327. Min Act: -0.1700

Data Index: 7193663 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2367. Min Act: -0.1700

Data Index: 7410168 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2495. Min Act: -0.1700

Data Index: 6655911 (Open Web Text)

Max Activating Token Index: 948

Text #13

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2418. Min Act: -0.1700

Data Index: 2616494 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2092. Min Act: -0.1700

Data Index: 5194878 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2191. Min Act: -0.1700

Data Index: 1317665 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2405. Min Act: -0.1700

Data Index: 3464775 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2294. Min Act: -0.1700

Data Index: 3063913 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2031. Min Act: -0.1700

Data Index: 5046906 (Open Web Text)

Max Activating Token Index: 151

Text #19

Max Range: 3.2865. Min Range: -3.2865

Max Act: 3.2135. Min Act: -0.1700

Data Index: 5388384 (Open Web Text)

Max Activating Token Index: 233