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

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

Neuron 600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2919. Min Range: -6.2919

Max Act: 6.2919. Min Act: -0.0000

Data Index: 663745 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.3790. Min Act: -0.0000

Data Index: 918481 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.9041. Min Act: -0.0000

Data Index: 151088 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.8940. Min Act: -0.0000

Data Index: 1201309 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.8184. Min Act: -0.0000

Data Index: 240393 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.7554. Min Act: -0.0000

Data Index: 642045 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.5305. Min Act: -0.0000

Data Index: 259898 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.7882. Min Act: -0.0000

Data Index: 982820 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.2275. Min Act: -0.0000

Data Index: 171826 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.9866. Min Act: -0.0000

Data Index: 884993 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.1474. Min Act: -0.0000

Data Index: 533356 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 6.2919. Min Range: -6.2919

Max Act: 5.2575. Min Act: -0.0000

Data Index: 1316874 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.8403. Min Act: -0.0000

Data Index: 686547 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.7033. Min Act: -0.0000

Data Index: 1310137 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.9163. Min Act: -0.0000

Data Index: 1021581 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.6419. Min Act: -0.0000

Data Index: 562171 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.6051. Min Act: -0.0000

Data Index: 98320 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.8073. Min Act: -0.0000

Data Index: 645535 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.7916. Min Act: -0.0000

Data Index: 787647 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 6.2919. Min Range: -6.2919

Max Act: 4.5996. Min Act: -0.0000

Data Index: 2083 (C4 (Web Text))

Max Activating Token Index: 186