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

Dataset: Open Web Text

Neuron 2980 in Layer 2

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: 1.5049. Min Range: -1.5049

Max Act: 1.4944. Min Act: -0.1700

Data Index: 6807608 (Open Web Text)

Max Activating Token Index: 917

Text #1

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4805. Min Act: -0.1700

Data Index: 7415093 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4734. Min Act: -0.1700

Data Index: 839338 (Open Web Text)

Max Activating Token Index: 926

Text #3

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4925. Min Act: -0.1700

Data Index: 2381760 (Open Web Text)

Max Activating Token Index: 932

Text #4

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.5049. Min Act: -0.1700

Data Index: 2850399 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4701. Min Act: -0.1700

Data Index: 7228948 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4822. Min Act: -0.1700

Data Index: 5271375 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4581. Min Act: -0.1700

Data Index: 6003323 (Open Web Text)

Max Activating Token Index: 888

Text #8

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4443. Min Act: -0.1700

Data Index: 783671 (Open Web Text)

Max Activating Token Index: 884

Text #9

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4389. Min Act: -0.1700

Data Index: 5863556 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4467. Min Act: -0.1700

Data Index: 1026896 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4482. Min Act: -0.1700

Data Index: 8623559 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4352. Min Act: -0.1700

Data Index: 2924565 (Open Web Text)

Max Activating Token Index: 876

Text #13

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4329. Min Act: -0.1700

Data Index: 2570271 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4257. Min Act: -0.1700

Data Index: 4611537 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4272. Min Act: -0.1700

Data Index: 7276633 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4385. Min Act: -0.1700

Data Index: 2361242 (Open Web Text)

Max Activating Token Index: 880

Text #17

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4135. Min Act: -0.1700

Data Index: 3251371 (Open Web Text)

Max Activating Token Index: 877

Text #18

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4241. Min Act: -0.1700

Data Index: 390243 (Open Web Text)

Max Activating Token Index: 873

Text #19

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4140. Min Act: -0.1700

Data Index: 6508906 (Open Web Text)

Max Activating Token Index: 867