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

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

Neuron 2731 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.7210. Min Act: -0.0001

Data Index: 30954 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6164. Min Act: -0.0001

Data Index: 353473 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6740. Min Act: -0.0001

Data Index: 1242721 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6761. Min Act: -0.0002

Data Index: 617053 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6335. Min Act: -0.0002

Data Index: 303034 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5669. Min Act: -0.0001

Data Index: 476394 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5450. Min Act: -0.0001

Data Index: 409151 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5773. Min Act: -0.0002

Data Index: 731789 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5843. Min Act: -0.0001

Data Index: 178662 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5763. Min Act: -0.0001

Data Index: 883727 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5589. Min Act: -0.0001

Data Index: 565726 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5202. Min Act: -0.0002

Data Index: 328442 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5408. Min Act: -0.0001

Data Index: 1083684 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5508. Min Act: -0.0002

Data Index: 1047080 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5136. Min Act: -0.0001

Data Index: 422457 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5438. Min Act: -0.0001

Data Index: 713064 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4939. Min Act: -0.0002

Data Index: 1303001 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5206. Min Act: -0.0002

Data Index: 172405 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4605. Min Act: -0.0002

Data Index: 515110 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5222. Min Act: -0.0001

Data Index: 497417 (C4 (Web Text))

Max Activating Token Index: 865