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

Dataset: Open Web Text

Neuron 450 in Layer 5

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: 4.0034. Min Range: -4.0034

Max Act: 4.0034. Min Act: -0.1700

Data Index: 2357090 (Open Web Text)

Max Activating Token Index: 913

Text #1

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.8319. Min Act: -0.1700

Data Index: 5618694 (Open Web Text)

Max Activating Token Index: 634

Text #2

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.8151. Min Act: -0.1700

Data Index: 251395 (Open Web Text)

Max Activating Token Index: 284

Text #3

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7666. Min Act: -0.1700

Data Index: 2420186 (Open Web Text)

Max Activating Token Index: 792

Text #4

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7764. Min Act: -0.1700

Data Index: 4238523 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7637. Min Act: -0.1700

Data Index: 8410446 (Open Web Text)

Max Activating Token Index: 310

Text #6

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7407. Min Act: -0.1700

Data Index: 4905560 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7471. Min Act: -0.1700

Data Index: 4823785 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7354. Min Act: -0.1700

Data Index: 5274993 (Open Web Text)

Max Activating Token Index: 761

Text #9

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7114. Min Act: -0.1700

Data Index: 883523 (Open Web Text)

Max Activating Token Index: 216

Text #10

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7237. Min Act: -0.1700

Data Index: 7239878 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7392. Min Act: -0.1700

Data Index: 979547 (Open Web Text)

Max Activating Token Index: 991

Text #12

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7500. Min Act: -0.1700

Data Index: 2742341 (Open Web Text)

Max Activating Token Index: 547

Text #13

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7045. Min Act: -0.1700

Data Index: 8236467 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6833. Min Act: -0.1700

Data Index: 2219956 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6866. Min Act: -0.1700

Data Index: 4400113 (Open Web Text)

Max Activating Token Index: 627

Text #16

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6867. Min Act: -0.1700

Data Index: 3034652 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6859. Min Act: -0.1700

Data Index: 2472003 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6890. Min Act: -0.1700

Data Index: 3693861 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7094. Min Act: -0.1700

Data Index: 3515161 (Open Web Text)

Max Activating Token Index: 958