Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.9181. Min Act: -0.1700

Data Index: 24219 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.6678. Min Act: -0.1700

Data Index: 363223 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.5426. Min Act: -0.1700

Data Index: 1071910 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.5426. Min Act: -0.1700

Data Index: 550141 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.5269. Min Act: -0.1700

Data Index: 771395 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.5269. Min Act: -0.1700

Data Index: 299346 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.5113. Min Act: -0.1700

Data Index: 1223422 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.5113. Min Act: -0.1700

Data Index: 966308 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4799. Min Act: -0.1700

Data Index: 488149 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4643. Min Act: -0.1700

Data Index: 266627 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4799. Min Act: -0.1700

Data Index: 687356 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4956. Min Act: -0.1700

Data Index: 524180 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4643. Min Act: -0.1700

Data Index: 388493 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4643. Min Act: -0.1700

Data Index: 258961 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4329. Min Act: -0.1700

Data Index: 736031 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4329. Min Act: -0.1700

Data Index: 1094538 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4643. Min Act: -0.1700

Data Index: 623819 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4329. Min Act: -0.1700

Data Index: 916450 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.4486. Min Act: -0.1700

Data Index: 687074 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 3.9181. Min Range: -3.9181

Max Act: 3.3858. Min Act: -0.1700

Data Index: 1144285 (C4 (Web Text))

Max Activating Token Index: 597