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

Dataset: Open Web Text

Neuron 1829 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: 3.6768. Min Range: -3.6768

Max Act: 3.6768. Min Act: -0.1700

Data Index: 4026702 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.5896. Min Act: -0.1700

Data Index: 4026703 (Open Web Text)

Max Activating Token Index: 71

Text #2

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.5707. Min Act: -0.1700

Data Index: 8331419 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.4464. Min Act: -0.1700

Data Index: 265199 (Open Web Text)

Max Activating Token Index: 579

Text #4

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.4293. Min Act: -0.1700

Data Index: 6364217 (Open Web Text)

Max Activating Token Index: 804

Text #5

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3998. Min Act: -0.1700

Data Index: 8715171 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3831. Min Act: -0.1700

Data Index: 1456064 (Open Web Text)

Max Activating Token Index: 983

Text #7

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3516. Min Act: -0.1700

Data Index: 4954829 (Open Web Text)

Max Activating Token Index: 788

Text #8

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3675. Min Act: -0.1700

Data Index: 7956791 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3342. Min Act: -0.1700

Data Index: 4547595 (Open Web Text)

Max Activating Token Index: 935

Text #10

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3540. Min Act: -0.1700

Data Index: 7738339 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3584. Min Act: -0.1700

Data Index: 1483036 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3505. Min Act: -0.1700

Data Index: 7474094 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3281. Min Act: -0.1700

Data Index: 4942211 (Open Web Text)

Max Activating Token Index: 596

Text #14

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3152. Min Act: -0.1700

Data Index: 7047667 (Open Web Text)

Max Activating Token Index: 97

Text #15

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3304. Min Act: -0.1700

Data Index: 6292205 (Open Web Text)

Max Activating Token Index: 138

Text #16

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3111. Min Act: -0.1700

Data Index: 6068199 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.2935. Min Act: -0.1700

Data Index: 2329289 (Open Web Text)

Max Activating Token Index: 117

Text #18

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.2986. Min Act: -0.1700

Data Index: 3128804 (Open Web Text)

Max Activating Token Index: 285

Text #19

Max Range: 3.6768. Min Range: -3.6768

Max Act: 3.3146. Min Act: -0.1700

Data Index: 3030589 (Open Web Text)

Max Activating Token Index: 727