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

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

Neuron 1945 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.6730. Min Act: -0.0001

Data Index: 714263 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.6601. Min Act: -0.0001

Data Index: 1077646 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5932. Min Act: -0.0000

Data Index: 567907 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5970. Min Act: -0.0001

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1174710 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1067424 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5388. Min Act: -0.0000

Data Index: 912068 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.3967. Min Act: -0.0000

Data Index: 656215 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5098. Min Act: -0.0001

Data Index: 1497086 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.4907. Min Act: -0.0001

Data Index: 901161 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.4848. Min Act: -0.0001

Data Index: 58054 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5266. Min Act: -0.0001

Data Index: 112158 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5443. Min Act: -0.0000

Data Index: 431515 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.4818. Min Act: -0.0001

Data Index: 107219 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5351. Min Act: -0.0001

Data Index: 54165 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5351. Min Act: -0.0001

Data Index: 909334 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5140. Min Act: -0.0001

Data Index: 999324 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5024. Min Act: -0.0001

Data Index: 78760 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5087. Min Act: -0.0000

Data Index: 277680 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.6730. Min Range: -0.6730

Max Act: 0.5105. Min Act: -0.0001

Data Index: 150731 (C4 (Web Text))

Max Activating Token Index: 10