Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.5610. Min Act: -0.0000

Data Index: 52667 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4957. Min Act: -0.0000

Data Index: 81002 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4880. Min Act: -0.0000

Data Index: 698967 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1114091 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4587. Min Act: -0.0000

Data Index: 883283 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4405. Min Act: -0.0000

Data Index: 678285 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4228. Min Act: -0.0000

Data Index: 729705 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4029. Min Act: -0.0000

Data Index: 976346 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4042. Min Act: -0.0000

Data Index: 583947 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4082. Min Act: -0.0000

Data Index: 463960 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4122. Min Act: -0.0001

Data Index: 471179 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4249. Min Act: -0.0000

Data Index: 168477 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4159. Min Act: -0.0000

Data Index: 192671 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.3867. Min Act: -0.0000

Data Index: 701361 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1189524 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1174729 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.3948. Min Act: -0.0000

Data Index: 84762 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.3929. Min Act: -0.0000

Data Index: 12924 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.3801. Min Act: -0.0000

Data Index: 449031 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.5610. Min Range: -0.5610

Max Act: 0.4069. Min Act: -0.0001

Data Index: 781180 (C4 (Web Text))

Max Activating Token Index: 290