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

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

Neuron 3632 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: 1.8507. Min Range: -1.8507

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1130831 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1287739 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.4898. Min Act: -0.0000

Data Index: 263862 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.4840. Min Act: -0.0000

Data Index: 910585 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1102293 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.3975. Min Act: -0.0000

Data Index: 73024 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.0970. Min Act: -0.0000

Data Index: 190580 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.4254. Min Act: -0.0000

Data Index: 129026 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1175980 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.3908. Min Act: -0.0000

Data Index: 167737 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.2810. Min Act: -0.0000

Data Index: 638224 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1311315 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.2779. Min Act: -0.0000

Data Index: 1186939 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1044264 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.3447. Min Act: -0.0000

Data Index: 409419 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.3147. Min Act: -0.0000

Data Index: 320017 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.4434. Min Act: -0.0000

Data Index: 739787 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.4377. Min Act: -0.0000

Data Index: 70208 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1008935 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.8507. Min Range: -1.8507

Max Act: 1.2725. Min Act: -0.0000

Data Index: 213029 (C4 (Web Text))

Max Activating Token Index: 828