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

Dataset: Open Web Text

Neuron 1922 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: 1.5120. Min Range: -1.5120

Max Act: 1.5120. Min Act: -0.0897

Data Index: 3665388 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4957. Min Act: -0.1330

Data Index: 6388286 (Open Web Text)

Max Activating Token Index: 991

Text #2

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4764. Min Act: -0.1135

Data Index: 8444052 (Open Web Text)

Max Activating Token Index: 970

Text #3

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4404. Min Act: -0.0897

Data Index: 3711109 (Open Web Text)

Max Activating Token Index: 570

Text #4

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4446. Min Act: -0.1696

Data Index: 714791 (Open Web Text)

Max Activating Token Index: 71

Text #5

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4409. Min Act: -0.1647

Data Index: 5411257 (Open Web Text)

Max Activating Token Index: 1004

Text #6

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4423. Min Act: -0.1329

Data Index: 736959 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4319. Min Act: -0.1161

Data Index: 4562801 (Open Web Text)

Max Activating Token Index: 570

Text #8

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4454. Min Act: -0.1331

Data Index: 5914330 (Open Web Text)

Max Activating Token Index: 1018

Text #9

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4315. Min Act: -0.1538

Data Index: 6995180 (Open Web Text)

Max Activating Token Index: 965

Text #10

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4241. Min Act: -0.1385

Data Index: 2264884 (Open Web Text)

Max Activating Token Index: 923

Text #11

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4349. Min Act: -0.1658

Data Index: 5547010 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4279. Min Act: -0.1676

Data Index: 1385422 (Open Web Text)

Max Activating Token Index: 991

Text #13

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4286. Min Act: -0.1657

Data Index: 7827343 (Open Web Text)

Max Activating Token Index: 989

Text #14

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4292. Min Act: -0.0897

Data Index: 1602733 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4170. Min Act: -0.0955

Data Index: 2111404 (Open Web Text)

Max Activating Token Index: 967

Text #16

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4251. Min Act: -0.1183

Data Index: 7810850 (Open Web Text)

Max Activating Token Index: 168

Text #17

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4184. Min Act: -0.1700

Data Index: 5914329 (Open Web Text)

Max Activating Token Index: 965

Text #18

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4243. Min Act: -0.0897

Data Index: 208273 (Open Web Text)

Max Activating Token Index: 835

Text #19

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4183. Min Act: -0.1614

Data Index: 5633773 (Open Web Text)

Max Activating Token Index: 514