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

Dataset: Open Web Text

Neuron 1602 in Layer 0

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: 4.8098. Min Range: -4.8098

Max Act: 4.8098. Min Act: -0.1700

Data Index: 6267935 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.7796. Min Act: -0.1700

Data Index: 5221989 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.7622. Min Act: -0.1700

Data Index: 8766733 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.7183. Min Act: -0.1700

Data Index: 5148524 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6818. Min Act: -0.1700

Data Index: 2560673 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6718. Min Act: -0.1700

Data Index: 668233 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6629. Min Act: -0.1700

Data Index: 5643535 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6734. Min Act: -0.1700

Data Index: 6896612 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6822. Min Act: -0.1700

Data Index: 8584658 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6474. Min Act: -0.1700

Data Index: 1727128 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6112. Min Act: -0.1700

Data Index: 5595248 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6149. Min Act: -0.1700

Data Index: 3943623 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6213. Min Act: -0.1700

Data Index: 3904870 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6166. Min Act: -0.1700

Data Index: 5380498 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6166. Min Act: -0.1700

Data Index: 844827 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6393. Min Act: -0.1700

Data Index: 8661495 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6166. Min Act: -0.1700

Data Index: 163721 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6036. Min Act: -0.1700

Data Index: 5220180 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.5908. Min Act: -0.1700

Data Index: 5871335 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.8098. Min Range: -4.8098

Max Act: 4.6147. Min Act: -0.1700

Data Index: 133677 (Open Web Text)

Max Activating Token Index: 5