Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1550 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3164. Min Act: -0.0001

Data Index: 15703 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3360. Min Act: -0.0001

Data Index: 671081 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1232382 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3050. Min Act: -0.0001

Data Index: 772151 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3361. Min Act: -0.0001

Data Index: 621807 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3191. Min Act: -0.0001

Data Index: 860191 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3083. Min Act: -0.0001

Data Index: 412086 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3181. Min Act: -0.0001

Data Index: 252835 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3314. Min Act: -0.0001

Data Index: 251394 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2695. Min Act: -0.0001

Data Index: 362082 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3012. Min Act: -0.0001

Data Index: 961260 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.3005. Min Act: -0.0001

Data Index: 702685 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2601. Min Act: -0.0001

Data Index: 365591 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2903. Min Act: -0.0001

Data Index: 1033791 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2755. Min Act: -0.0001

Data Index: 443151 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2995. Min Act: -0.0001

Data Index: 941594 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2805. Min Act: -0.0001

Data Index: 301496 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2964. Min Act: -0.0001

Data Index: 1244845 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2740. Min Act: -0.0001

Data Index: 889137 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2524. Min Act: -0.0001

Data Index: 816678 (C4 (Web Text))

Max Activating Token Index: 805