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

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

Neuron 3438 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.5146. Min Act: -0.0000

Data Index: 203223 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4477. Min Act: -0.0000

Data Index: 368309 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4451. Min Act: -0.0001

Data Index: 789360 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1000406 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3820. Min Act: -0.0000

Data Index: 191398 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1349847 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3664. Min Act: -0.0000

Data Index: 856643 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3790. Min Act: -0.0000

Data Index: 340218 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3555. Min Act: -0.0001

Data Index: 899921 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3680. Min Act: -0.0001

Data Index: 818641 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1003077 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1130366 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3257. Min Act: -0.0001

Data Index: 247477 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3296. Min Act: 0.0001

Data Index: 627680 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3342. Min Act: -0.0000

Data Index: 506351 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3257. Min Act: -0.0001

Data Index: 1201237 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3147. Min Act: -0.0000

Data Index: 186060 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3286. Min Act: -0.0000

Data Index: 255354 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1106074 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.5146. Min Range: -0.5146

Max Act: 0.3025. Min Act: -0.0001

Data Index: 421930 (C4 (Web Text))

Max Activating Token Index: 416