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

Dataset: Open Web Text

Neuron 1859 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: 3.6191. Min Range: -3.6191

Max Act: 3.6191. Min Act: -0.1700

Data Index: 5658939 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.6039. Min Act: -0.1700

Data Index: 7150706 (Open Web Text)

Max Activating Token Index: 617

Text #2

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.5847. Min Act: -0.1700

Data Index: 661977 (Open Web Text)

Max Activating Token Index: 905

Text #3

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.5585. Min Act: -0.1700

Data Index: 7932032 (Open Web Text)

Max Activating Token Index: 356

Text #4

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.5424. Min Act: -0.1700

Data Index: 2141167 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.5189. Min Act: -0.1700

Data Index: 4237916 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4841. Min Act: -0.1700

Data Index: 572007 (Open Web Text)

Max Activating Token Index: 208

Text #7

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1002100 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4413. Min Act: -0.1700

Data Index: 2968533 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4331. Min Act: -0.1700

Data Index: 7975631 (Open Web Text)

Max Activating Token Index: 566

Text #10

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4460. Min Act: -0.1700

Data Index: 4635017 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4153. Min Act: -0.1700

Data Index: 5571108 (Open Web Text)

Max Activating Token Index: 790

Text #12

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4028. Min Act: -0.1700

Data Index: 7005009 (Open Web Text)

Max Activating Token Index: 892

Text #13

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.3996. Min Act: -0.1700

Data Index: 1151967 (Open Web Text)

Max Activating Token Index: 775

Text #14

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.4071. Min Act: -0.1700

Data Index: 8573590 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.3994. Min Act: -0.1700

Data Index: 4466189 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.3792. Min Act: -0.1700

Data Index: 7668746 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.3593. Min Act: -0.1700

Data Index: 3191451 (Open Web Text)

Max Activating Token Index: 294

Text #18

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.3740. Min Act: -0.1700

Data Index: 3088467 (Open Web Text)

Max Activating Token Index: 474

Text #19

Max Range: 3.6191. Min Range: -3.6191

Max Act: 3.3398. Min Act: -0.1700

Data Index: 2901906 (Open Web Text)

Max Activating Token Index: 749