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

Dataset: Open Web Text

Neuron 523 in Layer 2

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: 3.4647. Min Range: -3.4647

Max Act: 3.4647. Min Act: -0.1700

Data Index: 8077928 (Open Web Text)

Max Activating Token Index: 484

Text #1

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.2204. Min Act: -0.1700

Data Index: 776675 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.2021. Min Act: -0.1700

Data Index: 1582153 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.2038. Min Act: -0.1700

Data Index: 5979214 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.1602. Min Act: -0.1700

Data Index: 4322406 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.1345. Min Act: -0.1700

Data Index: 5814140 (Open Web Text)

Max Activating Token Index: 59

Text #6

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.1128. Min Act: -0.1700

Data Index: 3487102 (Open Web Text)

Max Activating Token Index: 788

Text #7

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0694. Min Act: -0.1700

Data Index: 2709993 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0904. Min Act: -0.1700

Data Index: 3733951 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.1078. Min Act: -0.1700

Data Index: 5228094 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0469. Min Act: -0.1700

Data Index: 5827205 (Open Web Text)

Max Activating Token Index: 159

Text #11

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0330. Min Act: -0.1700

Data Index: 6950444 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0167. Min Act: -0.1700

Data Index: 2939909 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0136. Min Act: -0.1700

Data Index: 4716241 (Open Web Text)

Max Activating Token Index: 252

Text #14

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.9890. Min Act: -0.1700

Data Index: 1578776 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.9841. Min Act: -0.1700

Data Index: 879778 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.9847. Min Act: -0.1700

Data Index: 7998509 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0149. Min Act: -0.1700

Data Index: 3811843 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.9871. Min Act: -0.1700

Data Index: 1887030 (Open Web Text)

Max Activating Token Index: 696

Text #19

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.9927. Min Act: -0.1700

Data Index: 4267384 (Open Web Text)

Max Activating Token Index: 63