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

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

Neuron 1775 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9409. Min Range: -4.9409

Max Act: 4.9409. Min Act: -0.0000

Data Index: 1181754 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 4.9409. Min Range: -4.9409

Max Act: 4.0485. Min Act: -0.0001

Data Index: 884236 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 4.9409. Min Range: -4.9409

Max Act: 4.0270. Min Act: 0.0000

Data Index: 870529 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.5290. Min Act: -0.0000

Data Index: 670207 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.4378. Min Act: -0.0001

Data Index: 985182 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.6165. Min Act: -0.0001

Data Index: 1193811 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.4625. Min Act: -0.0001

Data Index: 1033969 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.4369. Min Act: -0.0001

Data Index: 7247 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.6321. Min Act: -0.0001

Data Index: 287135 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.3836. Min Act: -0.0000

Data Index: 943344 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 4.9409. Min Range: -4.9409

Max Act: 3.1176. Min Act: -0.0000

Data Index: 656383 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 4.9409. Min Range: -4.9409

Max Act: 1.8759. Min Act: -0.0000

Data Index: 82479 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.4891. Min Act: -0.0001

Data Index: 324084 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.9585. Min Act: -0.0001

Data Index: 957479 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.7969. Min Act: -0.0000

Data Index: 305524 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.4624. Min Act: -0.0000

Data Index: 195731 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.4697. Min Act: -0.0000

Data Index: 430948 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.0852. Min Act: -0.0001

Data Index: 48925 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.5305. Min Act: -0.0001

Data Index: 693441 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 4.9409. Min Range: -4.9409

Max Act: 2.3328. Min Act: -0.0001

Data Index: 75762 (C4 (Web Text))

Max Activating Token Index: 140