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

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

Neuron 1500 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: 4.1456. Min Range: -4.1456

Max Act: 4.1456. Min Act: -0.1699

Data Index: 398803 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.8441. Min Act: -0.1700

Data Index: 680565 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.7728. Min Act: -0.1700

Data Index: 196089 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.7431. Min Act: -0.1700

Data Index: 736322 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.7121. Min Act: -0.1698

Data Index: 1370079 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6927. Min Act: -0.1700

Data Index: 926702 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6909. Min Act: -0.1700

Data Index: 836126 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6552. Min Act: -0.1700

Data Index: 195996 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6585. Min Act: -0.1700

Data Index: 1381316 (Python Code)

Max Activating Token Index: 771

Text #9

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6285. Min Act: -0.1700

Data Index: 106547 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6169. Min Act: -0.1696

Data Index: 456710 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6178. Min Act: -0.1700

Data Index: 38275 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.6088. Min Act: -0.1700

Data Index: 14117 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.5896. Min Act: -0.1700

Data Index: 461899 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.5753. Min Act: -0.1700

Data Index: 793380 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.5897. Min Act: -0.1700

Data Index: 1213000 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.5944. Min Act: -0.1700

Data Index: 422689 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.5701. Min Act: -0.1699

Data Index: 1577071 (Python Code)

Max Activating Token Index: 296

Text #18

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.5623. Min Act: -0.1700

Data Index: 1621035 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 4.1456. Min Range: -4.1456

Max Act: 3.5569. Min Act: -0.1700

Data Index: 1507643 (Python Code)

Max Activating Token Index: 578