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

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

Neuron 1176 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.3964. Min Act: -0.1700

Data Index: 479419 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.3964. Min Act: -0.1700

Data Index: 1461158 (Python Code)

Max Activating Token Index: 117

Text #2

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2714. Min Act: -0.1700

Data Index: 598994 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2714. Min Act: -0.1700

Data Index: 1209956 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2714. Min Act: -0.1700

Data Index: 437120 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2714. Min Act: -0.1700

Data Index: 805177 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2714. Min Act: -0.1700

Data Index: 436993 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2402. Min Act: -0.1700

Data Index: 168990 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2402. Min Act: -0.1700

Data Index: 268717 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2402. Min Act: -0.1700

Data Index: 1051746 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1777. Min Act: -0.1700

Data Index: 1370531 (Python Code)

Max Activating Token Index: 912

Text #11

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1777. Min Act: -0.1700

Data Index: 1134805 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1777. Min Act: -0.1700

Data Index: 958002 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1777. Min Act: -0.1700

Data Index: 556289 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1777. Min Act: -0.1700

Data Index: 583838 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1464. Min Act: -0.1700

Data Index: 167291 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1777. Min Act: -0.1700

Data Index: 1284997 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1464. Min Act: -0.1700

Data Index: 480708 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1464. Min Act: -0.1700

Data Index: 940724 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1464. Min Act: -0.1700

Data Index: 881897 (C4 (Web Text))

Max Activating Token Index: 151