Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1399 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4699. Min Act: -0.1700

Data Index: 1119968 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4856. Min Act: -0.1700

Data Index: 871514 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4385. Min Act: -0.1700

Data Index: 40508 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4385. Min Act: -0.1700

Data Index: 1080389 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4385. Min Act: -0.1700

Data Index: 1327522 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4229. Min Act: -0.1700

Data Index: 927799 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4072. Min Act: -0.1700

Data Index: 816077 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3758. Min Act: -0.1700

Data Index: 633072 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.4072. Min Act: -0.1700

Data Index: 445474 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3915. Min Act: -0.1700

Data Index: 267220 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3758. Min Act: -0.1700

Data Index: 726889 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3758. Min Act: -0.1700

Data Index: 235332 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3758. Min Act: -0.1700

Data Index: 790420 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3601. Min Act: -0.1700

Data Index: 1029472 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3601. Min Act: -0.1700

Data Index: 1114299 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3601. Min Act: -0.1700

Data Index: 423451 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3758. Min Act: -0.1700

Data Index: 948538 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3758. Min Act: -0.1700

Data Index: 370019 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3758. Min Act: -0.1700

Data Index: 526351 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 3.4856. Min Range: -3.4856

Max Act: 3.3444. Min Act: -0.1700

Data Index: 422360 (C4 (Web Text))

Max Activating Token Index: 459