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

Dataset: Open Web Text

Neuron 609 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: 2.9487. Min Range: -2.9487

Max Act: 2.9487. Min Act: -0.1700

Data Index: 186016 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.9278. Min Act: -0.1700

Data Index: 4989742 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8953. Min Act: -0.1700

Data Index: 3398882 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8853. Min Act: -0.1700

Data Index: 4892731 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8667. Min Act: -0.1700

Data Index: 6474471 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8404. Min Act: -0.1700

Data Index: 37144 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8466. Min Act: -0.1700

Data Index: 4359610 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8421. Min Act: -0.1700

Data Index: 4813210 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8395. Min Act: -0.1700

Data Index: 8487375 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8335. Min Act: -0.1700

Data Index: 6278765 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8300. Min Act: -0.1700

Data Index: 5939930 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8161. Min Act: -0.1700

Data Index: 2520892 (Open Web Text)

Max Activating Token Index: 555

Text #12

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8176. Min Act: -0.1700

Data Index: 2664880 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8209. Min Act: -0.1700

Data Index: 184984 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8097. Min Act: -0.1700

Data Index: 6732248 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8043. Min Act: -0.1700

Data Index: 1554917 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.8009. Min Act: -0.1700

Data Index: 3246727 (Open Web Text)

Max Activating Token Index: 61

Text #17

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.7907. Min Act: -0.1700

Data Index: 1458700 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.7972. Min Act: -0.1700

Data Index: 5857069 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.9487. Min Range: -2.9487

Max Act: 2.7892. Min Act: -0.1700

Data Index: 5382095 (Open Web Text)

Max Activating Token Index: 559