Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4752 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2931. Min Act: -0.0000

Data Index: 295374 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.3064. Min Act: -0.0000

Data Index: 862480 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2927. Min Act: -0.0000

Data Index: 506272 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2872. Min Act: -0.0000

Data Index: 276408 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2841. Min Act: -0.0000

Data Index: 453177 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2849. Min Act: -0.0000

Data Index: 247580 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2734. Min Act: -0.0000

Data Index: 584147 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2569. Min Act: -0.0000

Data Index: 682424 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1196617 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2351. Min Act: -0.0000

Data Index: 643576 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2335. Min Act: -0.0000

Data Index: 718165 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2249. Min Act: -0.0000

Data Index: 289024 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1324785 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2185. Min Act: -0.0000

Data Index: 707894 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2223. Min Act: -0.0000

Data Index: 284605 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2134. Min Act: -0.0000

Data Index: 476173 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1062528 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1053951 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.2041. Min Act: -0.0000

Data Index: 858724 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.3064. Min Range: -0.3064

Max Act: 0.1969. Min Act: -0.0000

Data Index: 389793 (C4 (Web Text))

Max Activating Token Index: 785