Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 5973 in Layer 25

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.8080. Min Act: -0.1700

Data Index: 2996683 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.7143. Min Act: -0.1700

Data Index: 400542 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 4484053 (Open Web Text)

Max Activating Token Index: 294

Text #3

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 7316130 (Open Web Text)

Max Activating Token Index: 230

Text #4

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 2554421 (Open Web Text)

Max Activating Token Index: 711

Text #5

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4643. Min Act: -0.1700

Data Index: 6828045 (Open Web Text)

Max Activating Token Index: 881

Text #6

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4330. Min Act: -0.1700

Data Index: 3268961 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4643. Min Act: -0.1700

Data Index: 6673266 (Open Web Text)

Max Activating Token Index: 245

Text #8

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4330. Min Act: -0.1700

Data Index: 3498630 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4018. Min Act: -0.1700

Data Index: 3073198 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4018. Min Act: -0.1700

Data Index: 6872242 (Open Web Text)

Max Activating Token Index: 159

Text #11

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3393. Min Act: -0.1700

Data Index: 3654987 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3705. Min Act: -0.1700

Data Index: 285737 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3705. Min Act: -0.1700

Data Index: 5027121 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3705. Min Act: -0.1700

Data Index: 3525676 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3705. Min Act: -0.1700

Data Index: 2275671 (Open Web Text)

Max Activating Token Index: 861

Text #16

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3705. Min Act: -0.1700

Data Index: 3477052 (Open Web Text)

Max Activating Token Index: 725

Text #17

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3393. Min Act: -0.1700

Data Index: 888953 (Open Web Text)

Max Activating Token Index: 134

Text #18

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3080. Min Act: -0.1700

Data Index: 3915961 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3080. Min Act: -0.1700

Data Index: 633262 (Open Web Text)

Max Activating Token Index: 358