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

Dataset: Open Web Text

Neuron 2245 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: 1.9681. Min Range: -1.9681

Max Act: 1.9681. Min Act: -0.1700

Data Index: 616099 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9591. Min Act: -0.1700

Data Index: 5535666 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9349. Min Act: -0.1700

Data Index: 8424599 (Open Web Text)

Max Activating Token Index: 132

Text #3

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9363. Min Act: -0.1700

Data Index: 5881875 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9362. Min Act: -0.1700

Data Index: 5744514 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9043. Min Act: -0.1700

Data Index: 716854 (Open Web Text)

Max Activating Token Index: 193

Text #6

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9174. Min Act: -0.1700

Data Index: 6660112 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8982. Min Act: -0.1700

Data Index: 6943 (Open Web Text)

Max Activating Token Index: 582

Text #8

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8897. Min Act: -0.1693

Data Index: 4848487 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8981. Min Act: -0.1700

Data Index: 8331335 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8920. Min Act: -0.1700

Data Index: 3829715 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8935. Min Act: -0.1700

Data Index: 1602023 (Open Web Text)

Max Activating Token Index: 833

Text #12

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8866. Min Act: -0.1700

Data Index: 2411809 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8803. Min Act: -0.1700

Data Index: 7934142 (Open Web Text)

Max Activating Token Index: 90

Text #14

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8781. Min Act: -0.1700

Data Index: 5403934 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8778. Min Act: -0.1700

Data Index: 6815669 (Open Web Text)

Max Activating Token Index: 135

Text #16

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8752. Min Act: -0.1700

Data Index: 2511034 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8723. Min Act: -0.1700

Data Index: 6120785 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8766. Min Act: -0.1700

Data Index: 6632475 (Open Web Text)

Max Activating Token Index: 708

Text #19

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8737. Min Act: -0.1700

Data Index: 57952 (Open Web Text)

Max Activating Token Index: 93