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

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

Neuron 960 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: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1247825 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6915. Min Act: -0.0000

Data Index: 757354 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8002. Min Act: -0.0000

Data Index: 52485 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7044. Min Act: -0.0001

Data Index: 490000 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1083999 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7404. Min Act: -0.0001

Data Index: 205277 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7285. Min Act: -0.0000

Data Index: 841424 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7647. Min Act: -0.0000

Data Index: 856577 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7633. Min Act: -0.0001

Data Index: 598957 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7098. Min Act: -0.0000

Data Index: 390931 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1009610 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6990. Min Act: -0.0000

Data Index: 362840 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7093. Min Act: -0.0000

Data Index: 74037 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6771. Min Act: -0.0000

Data Index: 114511 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6399. Min Act: -0.0001

Data Index: 344161 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1184045 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6988. Min Act: -0.0000

Data Index: 206443 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6583. Min Act: -0.0001

Data Index: 1068322 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6902. Min Act: -0.0001

Data Index: 18431 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6293. Min Act: -0.0001

Data Index: 550457 (C4 (Web Text))

Max Activating Token Index: 699