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

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

Neuron 1753 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.6933. Min Act: -0.1700

Data Index: 842802 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5837. Min Act: -0.1700

Data Index: 177085 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.6150. Min Act: -0.1700

Data Index: 111997 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5680. Min Act: -0.1700

Data Index: 1267583 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5524. Min Act: -0.1700

Data Index: 661483 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5680. Min Act: -0.1700

Data Index: 270178 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5211. Min Act: -0.1700

Data Index: 866835 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5054. Min Act: -0.1700

Data Index: 863405 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5211. Min Act: -0.1700

Data Index: 1164648 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5211. Min Act: -0.1700

Data Index: 976229 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5211. Min Act: -0.1700

Data Index: 390708 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5054. Min Act: -0.1700

Data Index: 131155 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5054. Min Act: -0.1700

Data Index: 342097 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5367. Min Act: -0.1700

Data Index: 1043570 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.4740. Min Act: -0.1700

Data Index: 492189 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5054. Min Act: -0.1700

Data Index: 350137 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5054. Min Act: -0.1700

Data Index: 1094514 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.4740. Min Act: -0.1700

Data Index: 507968 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.5054. Min Act: -0.1700

Data Index: 68210 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 3.6933. Min Range: -3.6933

Max Act: 3.4427. Min Act: -0.1700

Data Index: 1174647 (C4 (Web Text))

Max Activating Token Index: 800