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

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

Neuron 1122 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4956. Min Act: -0.0000

Data Index: 494433 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4946. Min Act: -0.0000

Data Index: 993880 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4090. Min Act: -0.0000

Data Index: 17995 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3933. Min Act: -0.0000

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1207336 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4216. Min Act: -0.0000

Data Index: 289949 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1256870 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1121744 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1216465 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3505. Min Act: -0.0000

Data Index: 989043 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1316500 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3599. Min Act: -0.0000

Data Index: 809044 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3374. Min Act: -0.0000

Data Index: 832922 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3689. Min Act: -0.0000

Data Index: 884652 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1243405 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3316. Min Act: -0.0000

Data Index: 517108 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3296. Min Act: -0.0000

Data Index: 337675 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3505. Min Act: -0.0000

Data Index: 831871 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3385. Min Act: -0.0000

Data Index: 473233 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3390. Min Act: -0.0000

Data Index: 548511 (C4 (Web Text))

Max Activating Token Index: 782