Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 408 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.6120. Min Act: -0.1700

Data Index: 1137878 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.5337. Min Act: -0.1700

Data Index: 53229 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.5337. Min Act: -0.1700

Data Index: 471681 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.5337. Min Act: -0.1700

Data Index: 1157990 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4710. Min Act: -0.1700

Data Index: 314259 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4240. Min Act: -0.1700

Data Index: 37425 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4083. Min Act: -0.1700

Data Index: 1104380 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4083. Min Act: -0.1700

Data Index: 1078086 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4240. Min Act: -0.1700

Data Index: 49464 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4397. Min Act: -0.1700

Data Index: 1330634 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4083. Min Act: -0.1700

Data Index: 735288 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4083. Min Act: -0.1700

Data Index: 781942 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4083. Min Act: -0.1700

Data Index: 412189 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4083. Min Act: -0.1700

Data Index: 989912 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4240. Min Act: -0.1700

Data Index: 1021444 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.4083. Min Act: -0.1700

Data Index: 141093 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3769. Min Act: -0.1700

Data Index: 1075891 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3769. Min Act: -0.1700

Data Index: 873294 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3612. Min Act: -0.1700

Data Index: 749428 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 3.6120. Min Range: -3.6120

Max Act: 3.3926. Min Act: -0.1700

Data Index: 170654 (C4 (Web Text))

Max Activating Token Index: 72