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

Dataset: Open Web Text

Neuron 2134 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: 4.6859. Min Range: -4.6859

Max Act: 4.6859. Min Act: -0.1700

Data Index: 5069434 (Open Web Text)

Max Activating Token Index: 832

Text #1

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.5822. Min Act: -0.1700

Data Index: 7505981 (Open Web Text)

Max Activating Token Index: 481

Text #2

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.5278. Min Act: -0.1700

Data Index: 8739112 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.5423. Min Act: -0.1700

Data Index: 6726550 (Open Web Text)

Max Activating Token Index: 170

Text #4

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.5052. Min Act: -0.1700

Data Index: 7493840 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.5224. Min Act: -0.1700

Data Index: 1767569 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4759. Min Act: -0.1700

Data Index: 7493274 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4547. Min Act: -0.1700

Data Index: 652091 (Open Web Text)

Max Activating Token Index: 151

Text #8

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4647. Min Act: -0.1700

Data Index: 3802072 (Open Web Text)

Max Activating Token Index: 835

Text #9

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4988. Min Act: -0.1700

Data Index: 1999284 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4240. Min Act: -0.1700

Data Index: 5951033 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.3991. Min Act: -0.1700

Data Index: 6121449 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.3904. Min Act: -0.1700

Data Index: 6253309 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4299. Min Act: -0.1700

Data Index: 3034047 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4137. Min Act: -0.1700

Data Index: 309668 (Open Web Text)

Max Activating Token Index: 447

Text #15

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4347. Min Act: -0.1700

Data Index: 7226524 (Open Web Text)

Max Activating Token Index: 101

Text #16

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.4306. Min Act: -0.1700

Data Index: 7279415 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.3874. Min Act: -0.1700

Data Index: 3550217 (Open Web Text)

Max Activating Token Index: 852

Text #18

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.3685. Min Act: -0.1700

Data Index: 2926103 (Open Web Text)

Max Activating Token Index: 432

Text #19

Max Range: 4.6859. Min Range: -4.6859

Max Act: 4.3600. Min Act: -0.1700

Data Index: 2266496 (Open Web Text)

Max Activating Token Index: 469