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

Dataset: Open Web Text

Neuron 2527 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: 4.8446. Min Range: -4.8446

Max Act: 4.8446. Min Act: -0.1700

Data Index: 3177657 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.7250. Min Act: -0.1700

Data Index: 5408518 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.7042. Min Act: -0.1700

Data Index: 4493623 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.7042. Min Act: -0.1700

Data Index: 4705830 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6621. Min Act: -0.1700

Data Index: 8101959 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6646. Min Act: -0.1700

Data Index: 3727525 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6382. Min Act: -0.1700

Data Index: 7515208 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6445. Min Act: -0.1700

Data Index: 4750126 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6247. Min Act: -0.1700

Data Index: 1609360 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6443. Min Act: -0.1700

Data Index: 6838480 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6046. Min Act: -0.1700

Data Index: 8474667 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6258. Min Act: -0.1700

Data Index: 8544204 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.6363. Min Act: -0.1700

Data Index: 5995296 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.5762. Min Act: -0.1700

Data Index: 7007781 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.5982. Min Act: -0.1700

Data Index: 3848833 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.5938. Min Act: -0.1700

Data Index: 6339985 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.5832. Min Act: -0.1700

Data Index: 1813565 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.5660. Min Act: -0.1700

Data Index: 5062582 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.5903. Min Act: -0.1700

Data Index: 4938707 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.8446. Min Range: -4.8446

Max Act: 4.5751. Min Act: -0.1700

Data Index: 3598950 (Open Web Text)

Max Activating Token Index: 8