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

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

Neuron 1691 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5330. Min Act: -0.0001

Data Index: 290150 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5443. Min Act: -0.0001

Data Index: 1203121 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5027. Min Act: -0.0001

Data Index: 988582 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4586. Min Act: -0.0001

Data Index: 1125912 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4699. Min Act: -0.0001

Data Index: 787425 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1232100 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4310. Min Act: -0.0001

Data Index: 554468 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4474. Min Act: -0.0001

Data Index: 576187 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4289. Min Act: -0.0001

Data Index: 26568 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4397. Min Act: -0.0001

Data Index: 975024 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4146. Min Act: -0.0001

Data Index: 162385 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3853. Min Act: -0.0001

Data Index: 979388 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3911. Min Act: -0.0001

Data Index: 826464 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3896. Min Act: -0.0001

Data Index: 408662 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3961. Min Act: -0.0001

Data Index: 722892 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3792. Min Act: -0.0001

Data Index: 1281792 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1215778 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3766. Min Act: -0.0001

Data Index: 1143943 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3661. Min Act: -0.0001

Data Index: 612577 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3676. Min Act: -0.0001

Data Index: 506042 (C4 (Web Text))

Max Activating Token Index: 316