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

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

Neuron 3280 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.5068. Min Act: -0.0001

Data Index: 1099303 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.5101. Min Act: -0.0001

Data Index: 877118 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4951. Min Act: -0.0001

Data Index: 24109 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4764. Min Act: -0.0001

Data Index: 1060067 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1093107 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4639. Min Act: -0.0001

Data Index: 828808 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4415. Min Act: -0.0001

Data Index: 1147908 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4532. Min Act: -0.0001

Data Index: 962242 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4160. Min Act: -0.0001

Data Index: 903090 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4422. Min Act: -0.0001

Data Index: 902745 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3630. Min Act: -0.0001

Data Index: 364451 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4154. Min Act: -0.0001

Data Index: 621605 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4214. Min Act: -0.0001

Data Index: 1161101 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4038. Min Act: -0.0001

Data Index: 19419 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4072. Min Act: -0.0001

Data Index: 523544 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4172. Min Act: -0.0001

Data Index: 895647 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4039. Min Act: -0.0001

Data Index: 29624 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4116. Min Act: -0.0001

Data Index: 791847 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4007. Min Act: -0.0001

Data Index: 269149 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4407. Min Act: -0.0001

Data Index: 51501 (C4 (Web Text))

Max Activating Token Index: 609