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

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

Neuron 57 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3205. Min Range: -1.3205

Max Act: 1.3205. Min Act: -0.0001

Data Index: 646189 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.3205. Min Range: -1.3205

Max Act: 1.2434. Min Act: -0.0001

Data Index: 1004798 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 1.3205. Min Range: -1.3205

Max Act: 1.0155. Min Act: -0.0001

Data Index: 153196 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.3205. Min Range: -1.3205

Max Act: 1.0448. Min Act: -0.0001

Data Index: 611138 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8926. Min Act: -0.0001

Data Index: 58802 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8890. Min Act: -0.0001

Data Index: 1329462 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.9056. Min Act: -0.0001

Data Index: 904455 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8686. Min Act: -0.0001

Data Index: 1133160 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.9295. Min Act: -0.0001

Data Index: 379068 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8690. Min Act: -0.0001

Data Index: 673400 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8398. Min Act: -0.0001

Data Index: 242757 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8418. Min Act: -0.0001

Data Index: 343172 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1184687 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8159. Min Act: -0.0001

Data Index: 416039 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8054. Min Act: -0.0001

Data Index: 872249 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.8025. Min Act: -0.0001

Data Index: 567064 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.7902. Min Act: -0.0001

Data Index: 1189244 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.7964. Min Act: -0.0001

Data Index: 370419 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.7614. Min Act: -0.0001

Data Index: 821442 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.3205. Min Range: -1.3205

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1121945 (C4 (Web Text))

Max Activating Token Index: 294