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

Dataset: Open Web Text

Neuron 1554 in Layer 1

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: 4.9124. Min Range: -4.9124

Max Act: 4.9124. Min Act: -0.1700

Data Index: 555990 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7904. Min Act: -0.1700

Data Index: 6216700 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7864. Min Act: -0.1700

Data Index: 8294731 (Open Web Text)

Max Activating Token Index: 619

Text #3

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7884. Min Act: -0.1700

Data Index: 3287332 (Open Web Text)

Max Activating Token Index: 925

Text #4

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7734. Min Act: -0.1700

Data Index: 4832103 (Open Web Text)

Max Activating Token Index: 955

Text #5

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7946. Min Act: -0.1700

Data Index: 5535054 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7806. Min Act: -0.1700

Data Index: 6136266 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7216. Min Act: -0.1700

Data Index: 392266 (Open Web Text)

Max Activating Token Index: 800

Text #8

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7593. Min Act: -0.1700

Data Index: 8138067 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7483. Min Act: -0.1700

Data Index: 7556699 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7329. Min Act: -0.1700

Data Index: 3441292 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7355. Min Act: -0.1700

Data Index: 7227422 (Open Web Text)

Max Activating Token Index: 202

Text #12

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7233. Min Act: -0.1700

Data Index: 6737914 (Open Web Text)

Max Activating Token Index: 992

Text #13

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7484. Min Act: -0.1700

Data Index: 1640818 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7654. Min Act: -0.1700

Data Index: 4685325 (Open Web Text)

Max Activating Token Index: 992

Text #15

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7565. Min Act: -0.1700

Data Index: 2713147 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7653. Min Act: -0.1700

Data Index: 2233101 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7075. Min Act: -0.1700

Data Index: 4389233 (Open Web Text)

Max Activating Token Index: 952

Text #18

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7179. Min Act: -0.1700

Data Index: 3989237 (Open Web Text)

Max Activating Token Index: 306

Text #19

Max Range: 4.9124. Min Range: -4.9124

Max Act: 4.7130. Min Act: -0.1700

Data Index: 4244402 (Open Web Text)

Max Activating Token Index: 980