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

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

Neuron 4092 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2787. Min Act: -0.0000

Data Index: 201293 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2763. Min Act: -0.0001

Data Index: 903030 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2609. Min Act: -0.0000

Data Index: 609598 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.1996. Min Act: -0.0000

Data Index: 249916 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2175. Min Act: -0.0000

Data Index: 977211 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.1976. Min Act: -0.0001

Data Index: 585720 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2199. Min Act: -0.0000

Data Index: 411582 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2214. Min Act: -0.0000

Data Index: 291894 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2138. Min Act: -0.0001

Data Index: 633 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2092. Min Act: -0.0000

Data Index: 351192 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2351. Min Act: -0.0000

Data Index: 216983 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1325713 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.1853. Min Act: -0.0000

Data Index: 494154 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1180902 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.1922. Min Act: -0.0001

Data Index: 872508 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2183. Min Act: -0.0001

Data Index: 766980 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.1958. Min Act: -0.0000

Data Index: 595281 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2045. Min Act: -0.0001

Data Index: 573201 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2048. Min Act: -0.0000

Data Index: 126528 (C4 (Web Text))

Max Activating Token Index: 153