Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4836 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.2777. Min Act: -0.0000

Data Index: 741290 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.4015. Min Act: -0.0000

Data Index: 137551 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.9428. Min Act: -0.0000

Data Index: 1221943 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.0329. Min Act: -0.0000

Data Index: 878660 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.2158. Min Act: -0.0000

Data Index: 240206 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.1000. Min Act: -0.0000

Data Index: 617304 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.9911. Min Act: -0.0000

Data Index: 1033269 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.9163. Min Act: -0.0000

Data Index: 256414 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.8785. Min Act: -0.0000

Data Index: 64872 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.9510. Min Act: -0.0000

Data Index: 621690 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.9966. Min Act: -0.0000

Data Index: 1115954 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.7962. Min Act: -0.0000

Data Index: 356603 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 2.4015. Min Range: -2.4015

Max Act: 2.0596. Min Act: -0.0000

Data Index: 1253507 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.6163. Min Act: -0.0000

Data Index: 513588 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.8275. Min Act: -0.0000

Data Index: 162126 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.9123. Min Act: -0.0000

Data Index: 61343 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.6235. Min Act: -0.0000

Data Index: 111267 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.8072. Min Act: -0.0000

Data Index: 67076 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.5989. Min Act: -0.0000

Data Index: 913944 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 2.4015. Min Range: -2.4015

Max Act: 1.6983. Min Act: -0.0000

Data Index: 382558 (C4 (Web Text))

Max Activating Token Index: 1018