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

Dataset: Open Web Text

Neuron 480 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: 3.3114. Min Range: -3.3114

Max Act: 3.3070. Min Act: -0.1700

Data Index: 2267827 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.3114. Min Act: -0.1700

Data Index: 5268985 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.3061. Min Act: -0.1700

Data Index: 7330944 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2893. Min Act: -0.1700

Data Index: 6000792 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2241. Min Act: -0.1700

Data Index: 8408594 (Open Web Text)

Max Activating Token Index: 605

Text #5

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2620. Min Act: -0.1700

Data Index: 6387168 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2729. Min Act: -0.1700

Data Index: 6407414 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2473. Min Act: -0.1700

Data Index: 6885747 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2376. Min Act: -0.1700

Data Index: 3509761 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2186. Min Act: -0.1700

Data Index: 5818106 (Open Web Text)

Max Activating Token Index: 504

Text #10

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2589. Min Act: -0.1700

Data Index: 3090483 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2405. Min Act: -0.1700

Data Index: 7330136 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2062. Min Act: -0.1700

Data Index: 943351 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2251. Min Act: -0.1700

Data Index: 6861669 (Open Web Text)

Max Activating Token Index: 546

Text #14

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2340. Min Act: -0.1700

Data Index: 952851 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2042. Min Act: -0.1700

Data Index: 4716189 (Open Web Text)

Max Activating Token Index: 533

Text #16

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2310. Min Act: -0.1700

Data Index: 6590154 (Open Web Text)

Max Activating Token Index: 909

Text #17

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2173. Min Act: -0.1700

Data Index: 1347593 (Open Web Text)

Max Activating Token Index: 335

Text #18

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2168. Min Act: -0.1700

Data Index: 6441520 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 3.3114. Min Range: -3.3114

Max Act: 3.2071. Min Act: -0.1700

Data Index: 2490371 (Open Web Text)

Max Activating Token Index: 675