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

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

Neuron 1167 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0108. Min Range: -3.0108

Max Act: 3.0108. Min Act: -0.0001

Data Index: 869390 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 3.0108. Min Range: -3.0108

Max Act: 2.0132. Min Act: -0.0001

Data Index: 1033083 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.6743. Min Act: -0.0001

Data Index: 926321 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.7625. Min Act: -0.0001

Data Index: 273255 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.6544. Min Act: -0.0001

Data Index: 173789 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.5924. Min Act: -0.0001

Data Index: 857324 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.5030. Min Act: -0.0001

Data Index: 285221 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.4698. Min Act: -0.0001

Data Index: 809200 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.4281. Min Act: -0.0001

Data Index: 1157149 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.3313. Min Act: -0.0001

Data Index: 493864 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.4933. Min Act: -0.0001

Data Index: 681889 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.3197. Min Act: -0.0001

Data Index: 14784 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.3235. Min Act: -0.0001

Data Index: 53064 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.3224. Min Act: -0.0001

Data Index: 472719 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.2675. Min Act: -0.0001

Data Index: 1175056 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.1939. Min Act: -0.0001

Data Index: 5746 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.2697. Min Act: -0.0001

Data Index: 764392 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.3276. Min Act: -0.0001

Data Index: 195451 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.2285. Min Act: -0.0001

Data Index: 204076 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.0108. Min Range: -3.0108

Max Act: 1.2455. Min Act: -0.0001

Data Index: 301716 (C4 (Web Text))

Max Activating Token Index: 212