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

Dataset: Open Web Text

Neuron 2055 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: 3.4962. Min Range: -3.4962

Max Act: 3.4962. Min Act: -0.1700

Data Index: 6031251 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 3.4962. Min Range: -3.4962

Max Act: 3.3510. Min Act: -0.1700

Data Index: 5600818 (Open Web Text)

Max Activating Token Index: 1008

Text #2

Max Range: 3.4962. Min Range: -3.4962

Max Act: 3.1318. Min Act: -0.1700

Data Index: 4125516 (Open Web Text)

Max Activating Token Index: 191

Text #3

Max Range: 3.4962. Min Range: -3.4962

Max Act: 3.1204. Min Act: -0.1700

Data Index: 1953193 (Open Web Text)

Max Activating Token Index: 729

Text #4

Max Range: 3.4962. Min Range: -3.4962

Max Act: 3.0080. Min Act: -0.1700

Data Index: 2762179 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 3.4962. Min Range: -3.4962

Max Act: 3.0420. Min Act: -0.1700

Data Index: 7099542 (Open Web Text)

Max Activating Token Index: 193

Text #6

Max Range: 3.4962. Min Range: -3.4962

Max Act: 3.0300. Min Act: -0.1700

Data Index: 1524385 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.9469. Min Act: -0.1700

Data Index: 7356871 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8991. Min Act: -0.1700

Data Index: 3204323 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8999. Min Act: -0.1700

Data Index: 609021 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.9419. Min Act: -0.1700

Data Index: 6067203 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.9368. Min Act: -0.1700

Data Index: 6739954 (Open Web Text)

Max Activating Token Index: 134

Text #12

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.9038. Min Act: -0.1700

Data Index: 5053985 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8902. Min Act: -0.1700

Data Index: 4973668 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8487. Min Act: -0.1700

Data Index: 3273152 (Open Web Text)

Max Activating Token Index: 594

Text #15

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8387. Min Act: -0.1700

Data Index: 1834141 (Open Web Text)

Max Activating Token Index: 645

Text #16

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8460. Min Act: -0.1700

Data Index: 1853059 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8521. Min Act: -0.1700

Data Index: 189831 (Open Web Text)

Max Activating Token Index: 846

Text #18

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8143. Min Act: -0.1700

Data Index: 2873403 (Open Web Text)

Max Activating Token Index: 186

Text #19

Max Range: 3.4962. Min Range: -3.4962

Max Act: 2.8471. Min Act: -0.1700

Data Index: 4187374 (Open Web Text)

Max Activating Token Index: 623