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

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

Neuron 1466 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: 4.5344. Min Range: -4.5344

Max Act: 4.5344. Min Act: -0.1700

Data Index: 327778 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.5088. Min Act: -0.1700

Data Index: 521973 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4986. Min Act: -0.1700

Data Index: 487937 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.5079. Min Act: -0.1700

Data Index: 170635 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4780. Min Act: -0.1700

Data Index: 432994 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4890. Min Act: -0.1700

Data Index: 325411 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4970. Min Act: -0.1700

Data Index: 75010 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4511. Min Act: -0.1700

Data Index: 501084 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4625. Min Act: -0.1700

Data Index: 405265 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4233. Min Act: -0.1700

Data Index: 1041336 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.4228. Min Act: -0.1700

Data Index: 550892 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3792. Min Act: -0.1700

Data Index: 1058852 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3957. Min Act: -0.1700

Data Index: 497738 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3947. Min Act: -0.1700

Data Index: 935374 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3517. Min Act: -0.1700

Data Index: 73023 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3277. Min Act: -0.1700

Data Index: 1502946 (Python Code)

Max Activating Token Index: 555

Text #16

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3424. Min Act: -0.1700

Data Index: 886866 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3063. Min Act: -0.1700

Data Index: 1064455 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3491. Min Act: -0.1700

Data Index: 1152549 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 4.5344. Min Range: -4.5344

Max Act: 4.3343. Min Act: -0.1700

Data Index: 1070948 (C4 (Web Text))

Max Activating Token Index: 652