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

Dataset: Open Web Text

Neuron 2539 in Layer 3

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: 3.4147. Min Range: -3.4147

Max Act: 3.4147. Min Act: -0.1700

Data Index: 4521319 (Open Web Text)

Max Activating Token Index: 864

Text #1

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.4066. Min Act: -0.1700

Data Index: 5763116 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3599. Min Act: -0.1700

Data Index: 5610007 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3402. Min Act: -0.1700

Data Index: 8592265 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3435. Min Act: -0.1700

Data Index: 6969196 (Open Web Text)

Max Activating Token Index: 301

Text #5

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3428. Min Act: -0.1700

Data Index: 5278921 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3189. Min Act: -0.1700

Data Index: 8778987 (Open Web Text)

Max Activating Token Index: 686

Text #7

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3146. Min Act: -0.1700

Data Index: 6760557 (Open Web Text)

Max Activating Token Index: 195

Text #8

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1628464 (Open Web Text)

Max Activating Token Index: 499

Text #9

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3004. Min Act: -0.1700

Data Index: 5982016 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3033. Min Act: -0.1700

Data Index: 701753 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.3014. Min Act: -0.1700

Data Index: 6401624 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2830. Min Act: -0.1700

Data Index: 6078646 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2891. Min Act: -0.1700

Data Index: 4307396 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2565. Min Act: -0.1700

Data Index: 6773605 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2659. Min Act: -0.1700

Data Index: 2104446 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2495. Min Act: -0.1700

Data Index: 7302081 (Open Web Text)

Max Activating Token Index: 335

Text #17

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2489. Min Act: -0.1700

Data Index: 2030224 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2347. Min Act: -0.1700

Data Index: 7544983 (Open Web Text)

Max Activating Token Index: 825

Text #19

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2373. Min Act: -0.1700

Data Index: 6840769 (Open Web Text)

Max Activating Token Index: 104