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

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

Neuron 1363 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0003

Data Index: 931734 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0003

Data Index: 285387 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0003

Data Index: 437386 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 834844 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 637973 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 311210 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0003

Data Index: 564841 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 624503 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 570762 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 157259 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 423710 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 695562 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 170452 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 641150 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0003

Data Index: 856311 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1187476 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1084694 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 210795 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1083881 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0003

Data Index: 167148 (C4 (Web Text))

Max Activating Token Index: 747