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

Dataset: Open Web Text

Neuron 2028 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: 3.2975. Min Range: -3.2975

Max Act: 3.2975. Min Act: -0.1700

Data Index: 8051390 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1965. Min Act: -0.1700

Data Index: 6017146 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1848. Min Act: -0.1700

Data Index: 4422757 (Open Web Text)

Max Activating Token Index: 442

Text #3

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1772. Min Act: -0.1700

Data Index: 4097995 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1746. Min Act: -0.1700

Data Index: 757758 (Open Web Text)

Max Activating Token Index: 541

Text #5

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1573. Min Act: -0.1700

Data Index: 2604397 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1519. Min Act: -0.1700

Data Index: 6554481 (Open Web Text)

Max Activating Token Index: 755

Text #7

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1678. Min Act: -0.1700

Data Index: 3821885 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1351. Min Act: -0.1700

Data Index: 6793637 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1347. Min Act: -0.1700

Data Index: 2165716 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1510. Min Act: -0.1700

Data Index: 4896216 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1611. Min Act: -0.1700

Data Index: 6837329 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1412. Min Act: -0.1700

Data Index: 7708028 (Open Web Text)

Max Activating Token Index: 536

Text #13

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1321. Min Act: -0.1700

Data Index: 1570627 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1374. Min Act: -0.1700

Data Index: 6074017 (Open Web Text)

Max Activating Token Index: 542

Text #15

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1299. Min Act: -0.1700

Data Index: 3819387 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.0787. Min Act: -0.1700

Data Index: 7612285 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.0969. Min Act: -0.1700

Data Index: 7659560 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1059. Min Act: -0.1700

Data Index: 839662 (Open Web Text)

Max Activating Token Index: 529

Text #19

Max Range: 3.2975. Min Range: -3.2975

Max Act: 3.1110. Min Act: -0.1700

Data Index: 1582710 (Open Web Text)

Max Activating Token Index: 436