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

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

Neuron 524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3721. Min Act: -0.0000

Data Index: 197323 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3453. Min Act: -0.0000

Data Index: 337107 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1187168 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1129319 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3384. Min Act: -0.0001

Data Index: 451731 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3450. Min Act: -0.0000

Data Index: 218470 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3204. Min Act: -0.0000

Data Index: 2128 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3301. Min Act: 0.0000

Data Index: 370682 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2933. Min Act: -0.0001

Data Index: 483893 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3101. Min Act: 0.0000

Data Index: 399815 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1233563 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3177. Min Act: -0.0000

Data Index: 964186 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2677. Min Act: -0.0000

Data Index: 290772 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2978. Min Act: -0.0000

Data Index: 638689 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2822. Min Act: -0.0000

Data Index: 632940 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2989. Min Act: -0.0000

Data Index: 939338 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2845. Min Act: -0.0000

Data Index: 102918 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2752. Min Act: -0.0000

Data Index: 741080 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2843. Min Act: -0.0000

Data Index: 661566 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1210127 (C4 (Web Text))

Max Activating Token Index: 334