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

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

Neuron 3627 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0055. Min Range: -1.0055

Max Act: 1.0055. Min Act: -0.0001

Data Index: 1311140 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9118. Min Act: -0.0001

Data Index: 1126693 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9098. Min Act: -0.0001

Data Index: 772937 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8608. Min Act: -0.0001

Data Index: 482658 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8263. Min Act: -0.0001

Data Index: 106064 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8112. Min Act: -0.0001

Data Index: 728851 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7470. Min Act: -0.0001

Data Index: 546818 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7476. Min Act: -0.0001

Data Index: 87686 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7717. Min Act: -0.0001

Data Index: 856798 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7653. Min Act: -0.0001

Data Index: 1171578 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7901. Min Act: -0.0001

Data Index: 167825 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7536. Min Act: -0.0001

Data Index: 569658 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7659. Min Act: -0.0001

Data Index: 474239 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7386. Min Act: -0.0001

Data Index: 366752 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7574. Min Act: -0.0001

Data Index: 1186580 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7273. Min Act: -0.0001

Data Index: 835532 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7462. Min Act: -0.0001

Data Index: 172117 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1056649 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7327. Min Act: -0.0001

Data Index: 348577 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7053. Min Act: -0.0001

Data Index: 998102 (C4 (Web Text))

Max Activating Token Index: 646