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

Dataset: Open Web Text

Neuron 3025 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: 4.0538. Min Range: -4.0538

Max Act: 4.0538. Min Act: -0.1700

Data Index: 8810339 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 4.0538. Min Range: -4.0538

Max Act: 4.0504. Min Act: -0.1700

Data Index: 308171 (Open Web Text)

Max Activating Token Index: 35

Text #2

Max Range: 4.0538. Min Range: -4.0538

Max Act: 4.0459. Min Act: -0.1700

Data Index: 5669787 (Open Web Text)

Max Activating Token Index: 967

Text #3

Max Range: 4.0538. Min Range: -4.0538

Max Act: 4.0155. Min Act: -0.1700

Data Index: 7440440 (Open Web Text)

Max Activating Token Index: 712

Text #4

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9822. Min Act: -0.1700

Data Index: 8241650 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9956. Min Act: -0.1700

Data Index: 2052972 (Open Web Text)

Max Activating Token Index: 934

Text #6

Max Range: 4.0538. Min Range: -4.0538

Max Act: 4.0048. Min Act: -0.1700

Data Index: 2547979 (Open Web Text)

Max Activating Token Index: 980

Text #7

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9989. Min Act: -0.1700

Data Index: 6995127 (Open Web Text)

Max Activating Token Index: 380

Text #8

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9574. Min Act: -0.1700

Data Index: 1319368 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9409. Min Act: -0.1700

Data Index: 873181 (Open Web Text)

Max Activating Token Index: 248

Text #10

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9577. Min Act: -0.1700

Data Index: 8602373 (Open Web Text)

Max Activating Token Index: 162

Text #11

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9247. Min Act: -0.1700

Data Index: 6561399 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9411. Min Act: -0.1700

Data Index: 1988696 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.8778. Min Act: -0.1700

Data Index: 5664326 (Open Web Text)

Max Activating Token Index: 757

Text #14

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.8958. Min Act: -0.1700

Data Index: 6900135 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9139. Min Act: -0.1700

Data Index: 2498880 (Open Web Text)

Max Activating Token Index: 258

Text #16

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9059. Min Act: -0.1700

Data Index: 4667054 (Open Web Text)

Max Activating Token Index: 32

Text #17

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.8944. Min Act: -0.1700

Data Index: 3801910 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.8858. Min Act: -0.1700

Data Index: 6027266 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 4.0538. Min Range: -4.0538

Max Act: 3.9244. Min Act: -0.1700

Data Index: 7507046 (Open Web Text)

Max Activating Token Index: 274