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

Dataset: Open Web Text

Neuron 2294 in Layer 1

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: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.1700

Data Index: 6687979 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8689. Min Act: -0.1700

Data Index: 4085393 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8667. Min Act: -0.1700

Data Index: 3918207 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8634. Min Act: -0.1700

Data Index: 5331066 (Open Web Text)

Max Activating Token Index: 60

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8634. Min Act: -0.1700

Data Index: 27787 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8585. Min Act: -0.1700

Data Index: 644014 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8634. Min Act: -0.1700

Data Index: 107914 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8630. Min Act: -0.1700

Data Index: 5613652 (Open Web Text)

Max Activating Token Index: 52

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8567. Min Act: -0.1700

Data Index: 237417 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8601. Min Act: -0.1700

Data Index: 3181604 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8306. Min Act: -0.1700

Data Index: 7381693 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8302. Min Act: -0.1700

Data Index: 8681924 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8273. Min Act: -0.1700

Data Index: 7265044 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8256. Min Act: -0.1700

Data Index: 7085933 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8325. Min Act: -0.1700

Data Index: 1031220 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8318. Min Act: -0.1700

Data Index: 4852758 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8304. Min Act: -0.1700

Data Index: 6345325 (Open Web Text)

Max Activating Token Index: 56

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8214. Min Act: -0.1700

Data Index: 148825 (Open Web Text)

Max Activating Token Index: 59

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8246. Min Act: -0.1700

Data Index: 325029 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8263. Min Act: -0.1700

Data Index: 5364607 (Open Web Text)

Max Activating Token Index: 61