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

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

Neuron 1501 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.8277. Min Act: -0.1700

Data Index: 687407 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.7652. Min Act: -0.1700

Data Index: 892477 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.7339. Min Act: -0.1700

Data Index: 1218322 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6714. Min Act: -0.1700

Data Index: 84540 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.7027. Min Act: -0.1700

Data Index: 752644 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6714. Min Act: -0.1700

Data Index: 839280 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6714. Min Act: -0.1700

Data Index: 327803 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6089. Min Act: -0.1700

Data Index: 1247883 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6402. Min Act: -0.1700

Data Index: 590764 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6089. Min Act: -0.1700

Data Index: 472313 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6402. Min Act: -0.1700

Data Index: 1105897 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6402. Min Act: -0.1700

Data Index: 17487 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.6402. Min Act: -0.1699

Data Index: 215655 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.5777. Min Act: -0.1700

Data Index: 790332 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.5777. Min Act: -0.1700

Data Index: 281519 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.5777. Min Act: -0.1700

Data Index: 431389 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.5464. Min Act: -0.1700

Data Index: 424571 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.4839. Min Act: -0.1700

Data Index: 444288 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.5464. Min Act: -0.1700

Data Index: 743384 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 5.8277. Min Range: -5.8277

Max Act: 5.5152. Min Act: -0.1700

Data Index: 221928 (C4 (Web Text))

Max Activating Token Index: 300