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

Dataset: Open Web Text

Neuron 798 in Layer 5

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: 4.2963. Min Range: -4.2963

Max Act: 4.2963. Min Act: -0.1700

Data Index: 1010383 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.1541. Min Act: -0.1700

Data Index: 7249473 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.1483. Min Act: -0.1700

Data Index: 5151173 (Open Web Text)

Max Activating Token Index: 549

Text #3

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.1184. Min Act: -0.1700

Data Index: 6003840 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0461. Min Act: -0.1700

Data Index: 3567215 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0334. Min Act: -0.1700

Data Index: 8205236 (Open Web Text)

Max Activating Token Index: 486

Text #6

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0150. Min Act: -0.1700

Data Index: 2675160 (Open Web Text)

Max Activating Token Index: 152

Text #7

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0295. Min Act: -0.1700

Data Index: 72597 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0030. Min Act: -0.1700

Data Index: 1324758 (Open Web Text)

Max Activating Token Index: 513

Text #9

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0351. Min Act: -0.1700

Data Index: 6098861 (Open Web Text)

Max Activating Token Index: 480

Text #10

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0110. Min Act: -0.1700

Data Index: 4512200 (Open Web Text)

Max Activating Token Index: 906

Text #11

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0276. Min Act: -0.1700

Data Index: 4125481 (Open Web Text)

Max Activating Token Index: 578

Text #12

Max Range: 4.2963. Min Range: -4.2963

Max Act: 3.9804. Min Act: -0.1700

Data Index: 7023544 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 4.2963. Min Range: -4.2963

Max Act: 3.9837. Min Act: -0.1700

Data Index: 1741548 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 4.2963. Min Range: -4.2963

Max Act: 3.9984. Min Act: -0.1700

Data Index: 1746625 (Open Web Text)

Max Activating Token Index: 77

Text #15

Max Range: 4.2963. Min Range: -4.2963

Max Act: 3.9922. Min Act: -0.1700

Data Index: 7979419 (Open Web Text)

Max Activating Token Index: 971

Text #16

Max Range: 4.2963. Min Range: -4.2963

Max Act: 3.9762. Min Act: -0.1700

Data Index: 6175614 (Open Web Text)

Max Activating Token Index: 892

Text #17

Max Range: 4.2963. Min Range: -4.2963

Max Act: 3.9926. Min Act: -0.1700

Data Index: 3648669 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 4.2963. Min Range: -4.2963

Max Act: 4.0060. Min Act: -0.1700

Data Index: 2108834 (Open Web Text)

Max Activating Token Index: 700

Text #19

Max Range: 4.2963. Min Range: -4.2963

Max Act: 3.9971. Min Act: -0.1700

Data Index: 3799144 (Open Web Text)

Max Activating Token Index: 639