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

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

Neuron 3599 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: 0.3700. Min Range: -0.3700

Max Act: 0.3700. Min Act: -0.0001

Data Index: 50899 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3652. Min Act: -0.0001

Data Index: 340898 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3442. Min Act: -0.0000

Data Index: 554790 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3429. Min Act: -0.0001

Data Index: 770689 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3420. Min Act: -0.0000

Data Index: 666747 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3153. Min Act: -0.0001

Data Index: 1284727 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3286. Min Act: -0.0001

Data Index: 517800 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3301. Min Act: -0.0001

Data Index: 1080400 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3025. Min Act: -0.0000

Data Index: 966656 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3205. Min Act: -0.0001

Data Index: 979970 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3015. Min Act: -0.0001

Data Index: 168356 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3054. Min Act: -0.0001

Data Index: 1084649 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3042. Min Act: -0.0000

Data Index: 155595 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.3017. Min Act: -0.0001

Data Index: 892590 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2963. Min Act: -0.0000

Data Index: 81396 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2957. Min Act: -0.0001

Data Index: 890662 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2827. Min Act: -0.0001

Data Index: 459327 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2986. Min Act: -0.0000

Data Index: 324498 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1194497 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.3700. Min Range: -0.3700

Max Act: 0.2904. Min Act: -0.0000

Data Index: 742272 (C4 (Web Text))

Max Activating Token Index: 824