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

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

Neuron 724 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: 0.4956. Min Range: -0.4956

Max Act: 0.4956. Min Act: -0.0001

Data Index: 44602 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4667. Min Act: -0.0000

Data Index: 48983 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1178317 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4542. Min Act: -0.0000

Data Index: 508801 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4369. Min Act: -0.0001

Data Index: 947914 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4224. Min Act: -0.0000

Data Index: 691831 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1185069 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4239. Min Act: -0.0000

Data Index: 210131 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4208. Min Act: 0.0001

Data Index: 152190 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4273. Min Act: -0.0000

Data Index: 364872 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1200063 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3984. Min Act: -0.0001

Data Index: 433851 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4102. Min Act: -0.0000

Data Index: 691126 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4080. Min Act: 0.0000

Data Index: 255820 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4093. Min Act: -0.0000

Data Index: 387837 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4005. Min Act: -0.0000

Data Index: 361970 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4133. Min Act: -0.0000

Data Index: 490261 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4006. Min Act: 0.0000

Data Index: 991643 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3976. Min Act: -0.0000

Data Index: 982897 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4015. Min Act: -0.0000

Data Index: 70210 (C4 (Web Text))

Max Activating Token Index: 702