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

Dataset: Open Web Text

Neuron 2168 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: 3.9105. Min Range: -3.9105

Max Act: 3.9105. Min Act: -0.1700

Data Index: 1730636 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7823. Min Act: -0.1700

Data Index: 777879 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7902. Min Act: -0.1700

Data Index: 3797238 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7598. Min Act: -0.1700

Data Index: 8091380 (Open Web Text)

Max Activating Token Index: 786

Text #4

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7332. Min Act: -0.1700

Data Index: 7313877 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.7091. Min Act: -0.1700

Data Index: 7359023 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6591. Min Act: -0.1700

Data Index: 2980648 (Open Web Text)

Max Activating Token Index: 826

Text #7

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6409. Min Act: -0.1700

Data Index: 8796764 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6441. Min Act: -0.1700

Data Index: 1043050 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6592. Min Act: -0.1700

Data Index: 6464419 (Open Web Text)

Max Activating Token Index: 921

Text #10

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6374. Min Act: -0.1700

Data Index: 2103543 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1300137 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6183. Min Act: -0.1700

Data Index: 8811028 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6257. Min Act: -0.1700

Data Index: 4887057 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6428. Min Act: -0.1700

Data Index: 4519852 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6176. Min Act: -0.1700

Data Index: 7515932 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1763855 (Open Web Text)

Max Activating Token Index: 156

Text #17

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.5914. Min Act: -0.1700

Data Index: 2804599 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6135. Min Act: -0.1700

Data Index: 7022898 (Open Web Text)

Max Activating Token Index: 913

Text #19

Max Range: 3.9105. Min Range: -3.9105

Max Act: 3.6143. Min Act: -0.1700

Data Index: 7906736 (Open Web Text)

Max Activating Token Index: 415