Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1105687 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4587. Min Act: -0.0001

Data Index: 363762 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4390. Min Act: -0.0001

Data Index: 118389 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4157. Min Act: -0.0001

Data Index: 452884 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3706. Min Act: -0.0001

Data Index: 1260290 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3735. Min Act: -0.0001

Data Index: 544735 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3846. Min Act: -0.0001

Data Index: 208780 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1029981 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3639. Min Act: -0.0001

Data Index: 1307235 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3503. Min Act: -0.0001

Data Index: 217041 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3491. Min Act: -0.0001

Data Index: 156169 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3244. Min Act: -0.0001

Data Index: 44827 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1106886 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3315. Min Act: -0.0001

Data Index: 910422 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3311. Min Act: -0.0001

Data Index: 1304268 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3151. Min Act: -0.0001

Data Index: 32691 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1133383 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3172. Min Act: -0.0001

Data Index: 319574 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1175913 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3218. Min Act: -0.0001

Data Index: 761268 (C4 (Web Text))

Max Activating Token Index: 987