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

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

Neuron 67 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.9403. Min Act: -0.1700

Data Index: 624604 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8777. Min Act: -0.1700

Data Index: 1033892 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8464. Min Act: -0.1700

Data Index: 852136 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8777. Min Act: -0.1700

Data Index: 526089 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8152. Min Act: -0.1700

Data Index: 1286206 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8152. Min Act: -0.1700

Data Index: 351396 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8152. Min Act: -0.1700

Data Index: 977932 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8152. Min Act: -0.1700

Data Index: 785848 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8152. Min Act: -0.1700

Data Index: 1085193 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8152. Min Act: -0.1700

Data Index: 877294 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.8152. Min Act: -0.1700

Data Index: 325485 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7839. Min Act: -0.1700

Data Index: 745056 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7839. Min Act: -0.1700

Data Index: 476997 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7839. Min Act: -0.1700

Data Index: 276001 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7839. Min Act: -0.1700

Data Index: 1108689 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7839. Min Act: -0.1700

Data Index: 1350231 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7839. Min Act: -0.1700

Data Index: 289233 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7682. Min Act: -0.1700

Data Index: 217691 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7995. Min Act: -0.1700

Data Index: 1258483 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 3.9403. Min Range: -3.9403

Max Act: 3.7839. Min Act: -0.1700

Data Index: 271148 (C4 (Web Text))

Max Activating Token Index: 880