Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 40 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3510. Min Act: -0.0001

Data Index: 692590 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3669. Min Act: -0.0001

Data Index: 609661 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3473. Min Act: -0.0001

Data Index: 283356 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3260. Min Act: -0.0001

Data Index: 185276 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3388. Min Act: -0.0001

Data Index: 1105943 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1236517 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1200166 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3184. Min Act: -0.0001

Data Index: 467149 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1105084 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3302. Min Act: -0.0001

Data Index: 820437 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3374. Min Act: -0.0001

Data Index: 715556 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1347486 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3208. Min Act: -0.0001

Data Index: 996022 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3166. Min Act: -0.0001

Data Index: 563810 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2957. Min Act: -0.0001

Data Index: 131461 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3036. Min Act: -0.0001

Data Index: 128780 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3097. Min Act: -0.0001

Data Index: 1334893 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1082219 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1028549 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.3283. Min Act: -0.0001

Data Index: 29802 (C4 (Web Text))

Max Activating Token Index: 760