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

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

Neuron 1957 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.4198. Min Act: -0.1700

Data Index: 1217822 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.3884. Min Act: -0.1700

Data Index: 582998 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.3257. Min Act: -0.1700

Data Index: 791619 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.3571. Min Act: -0.1700

Data Index: 814983 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.3257. Min Act: -0.1700

Data Index: 157758 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.3257. Min Act: -0.1700

Data Index: 193634 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.2943. Min Act: -0.1700

Data Index: 153680 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.2628. Min Act: -0.1700

Data Index: 620482 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.2314. Min Act: -0.1700

Data Index: 356260 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.2314. Min Act: -0.1700

Data Index: 37011 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.2314. Min Act: -0.1700

Data Index: 433840 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.2314. Min Act: -0.1700

Data Index: 21791 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.1685. Min Act: -0.1700

Data Index: 238073 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.1685. Min Act: -0.1700

Data Index: 1234457 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.1685. Min Act: -0.1700

Data Index: 1238837 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.2314. Min Act: -0.1700

Data Index: 972541 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.1685. Min Act: -0.1700

Data Index: 1310442 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.1999. Min Act: -0.1700

Data Index: 551405 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.1685. Min Act: -0.1700

Data Index: 648814 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 3.4198. Min Range: -3.4198

Max Act: 3.1685. Min Act: -0.1700

Data Index: 306584 (C4 (Web Text))

Max Activating Token Index: 412