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

Dataset: Open Web Text

Neuron 1593 in Layer 4

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: 3.6961. Min Range: -3.6961

Max Act: 3.6961. Min Act: -0.1700

Data Index: 3059027 (Open Web Text)

Max Activating Token Index: 549

Text #1

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.6265. Min Act: -0.1700

Data Index: 5500054 (Open Web Text)

Max Activating Token Index: 803

Text #2

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5819. Min Act: -0.1700

Data Index: 3074256 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5723. Min Act: -0.1700

Data Index: 4237743 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5031. Min Act: -0.1700

Data Index: 3074255 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5013. Min Act: -0.1700

Data Index: 2993564 (Open Web Text)

Max Activating Token Index: 841

Text #6

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4872. Min Act: -0.1700

Data Index: 2871173 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4629. Min Act: -0.1700

Data Index: 7905598 (Open Web Text)

Max Activating Token Index: 975

Text #8

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4998. Min Act: -0.1700

Data Index: 4088070 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4659. Min Act: -0.1700

Data Index: 6225617 (Open Web Text)

Max Activating Token Index: 943

Text #10

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4574. Min Act: -0.1700

Data Index: 2499336 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4421. Min Act: -0.1700

Data Index: 6183146 (Open Web Text)

Max Activating Token Index: 52

Text #12

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4213. Min Act: -0.1700

Data Index: 270219 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4169. Min Act: -0.1700

Data Index: 8252412 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.3819. Min Act: -0.1700

Data Index: 1024264 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.3885. Min Act: -0.1700

Data Index: 1195081 (Open Web Text)

Max Activating Token Index: 318

Text #16

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.3883. Min Act: -0.1700

Data Index: 1700837 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4016. Min Act: -0.1700

Data Index: 6867231 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.3743. Min Act: -0.1700

Data Index: 2178538 (Open Web Text)

Max Activating Token Index: 982

Text #19

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.4036. Min Act: -0.1700

Data Index: 4671890 (Open Web Text)

Max Activating Token Index: 75