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

Dataset: Open Web Text

Neuron 2510 in Layer 6

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: 3.6201. Min Range: -3.6201

Max Act: 3.6201. Min Act: -0.1700

Data Index: 5966631 (Open Web Text)

Max Activating Token Index: 915

Text #1

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.4951. Min Act: -0.1700

Data Index: 8380404 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.4438. Min Act: -0.1700

Data Index: 5856763 (Open Web Text)

Max Activating Token Index: 965

Text #3

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.4234. Min Act: -0.1700

Data Index: 5338995 (Open Web Text)

Max Activating Token Index: 991

Text #4

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3985. Min Act: -0.1700

Data Index: 3457841 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3989. Min Act: -0.1700

Data Index: 2517895 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3932. Min Act: -0.1700

Data Index: 4830019 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3815. Min Act: -0.1700

Data Index: 8399164 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3537. Min Act: -0.1700

Data Index: 3021296 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3498. Min Act: -0.1700

Data Index: 5875438 (Open Web Text)

Max Activating Token Index: 1014

Text #10

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1460011 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3606. Min Act: -0.1700

Data Index: 982157 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3490. Min Act: -0.1700

Data Index: 786319 (Open Web Text)

Max Activating Token Index: 187

Text #13

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3648. Min Act: -0.1700

Data Index: 3413379 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3418. Min Act: -0.1700

Data Index: 8330571 (Open Web Text)

Max Activating Token Index: 827

Text #15

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3242. Min Act: -0.1700

Data Index: 7599331 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3376. Min Act: -0.1700

Data Index: 6346571 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3310. Min Act: -0.1700

Data Index: 1474600 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3155. Min Act: -0.1700

Data Index: 374351 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 3.6201. Min Range: -3.6201

Max Act: 3.3280. Min Act: -0.1700

Data Index: 1444707 (Open Web Text)

Max Activating Token Index: 995