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

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

Neuron 1728 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: 3.5984. Min Range: -3.5984

Max Act: 3.5984. Min Act: -0.1700

Data Index: 1617374 (Python Code)

Max Activating Token Index: 194

Text #1

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.4464. Min Act: -0.1700

Data Index: 1552258 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.4104. Min Act: -0.1700

Data Index: 105497 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3969. Min Act: -0.1700

Data Index: 1614967 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3669. Min Act: -0.1700

Data Index: 456289 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3795. Min Act: -0.1700

Data Index: 1471440 (Python Code)

Max Activating Token Index: 707

Text #6

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3718. Min Act: -0.1700

Data Index: 1599107 (Python Code)

Max Activating Token Index: 799

Text #7

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3620. Min Act: -0.1700

Data Index: 1388154 (Python Code)

Max Activating Token Index: 298

Text #8

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3256. Min Act: -0.1700

Data Index: 1583887 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3475. Min Act: -0.1700

Data Index: 308837 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.2920. Min Act: -0.1700

Data Index: 1273739 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3042. Min Act: -0.1700

Data Index: 1176763 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3526. Min Act: -0.1700

Data Index: 676729 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3106. Min Act: -0.1700

Data Index: 1255108 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3200. Min Act: -0.1700

Data Index: 1391819 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3123. Min Act: -0.1700

Data Index: 74943 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.2824. Min Act: -0.1700

Data Index: 69389 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3148. Min Act: -0.1700

Data Index: 177205 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.2856. Min Act: -0.1700

Data Index: 290323 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 3.5984. Min Range: -3.5984

Max Act: 3.3034. Min Act: -0.1700

Data Index: 1400299 (Python Code)

Max Activating Token Index: 208