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

Dataset: Open Web Text

Neuron 1026 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: 4.5655. Min Range: -4.5655

Max Act: 4.5655. Min Act: -0.1700

Data Index: 2553254 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.4273. Min Act: -0.1700

Data Index: 3371705 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.4188. Min Act: -0.1700

Data Index: 994717 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.4274. Min Act: -0.1700

Data Index: 314665 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.4286. Min Act: -0.1700

Data Index: 2856331 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3685. Min Act: -0.1700

Data Index: 95230 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3788. Min Act: -0.1700

Data Index: 7000998 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3777. Min Act: -0.1700

Data Index: 751686 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3788. Min Act: -0.1700

Data Index: 6856097 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3678. Min Act: -0.1700

Data Index: 5386014 (Open Web Text)

Max Activating Token Index: 40

Text #10

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3729. Min Act: -0.1700

Data Index: 951094 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3870. Min Act: -0.1700

Data Index: 2027734 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3429. Min Act: -0.1700

Data Index: 2606190 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3382. Min Act: -0.1700

Data Index: 524201 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3470. Min Act: -0.1700

Data Index: 3129248 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3719. Min Act: -0.1700

Data Index: 3503948 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3474. Min Act: -0.1700

Data Index: 3819719 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3501. Min Act: -0.1700

Data Index: 4336612 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3401. Min Act: -0.1700

Data Index: 4633198 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.5655. Min Range: -4.5655

Max Act: 4.3386. Min Act: -0.1700

Data Index: 5620580 (Open Web Text)

Max Activating Token Index: 4