Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 118 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.8193. Min Act: -0.1700

Data Index: 332510 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6771. Min Act: -0.1700

Data Index: 172108 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6496. Min Act: -0.1700

Data Index: 867913 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6557. Min Act: -0.1700

Data Index: 1220224 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6183. Min Act: -0.1700

Data Index: 1388501 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.6014. Min Act: -0.1700

Data Index: 59170 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5979. Min Act: -0.1700

Data Index: 51319 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5240. Min Act: -0.1700

Data Index: 322744 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5451. Min Act: -0.1700

Data Index: 1419075 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5201. Min Act: -0.1700

Data Index: 28127 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5507. Min Act: -0.1700

Data Index: 224940 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5218. Min Act: -0.1700

Data Index: 704441 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.4665. Min Act: -0.1700

Data Index: 279266 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.4697. Min Act: -0.1700

Data Index: 180982 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.5433. Min Act: -0.1700

Data Index: 1328235 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.4545. Min Act: -0.1700

Data Index: 619922 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.4489. Min Act: -0.1700

Data Index: 578536 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.4832. Min Act: -0.1700

Data Index: 1029149 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.4629. Min Act: -0.1700

Data Index: 248549 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 3.8193. Min Range: -3.8193

Max Act: 3.4596. Min Act: -0.1700

Data Index: 964947 (C4 (Web Text))

Max Activating Token Index: 959