Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4102 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1146130 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4919. Min Act: -0.0000

Data Index: 848265 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4138. Min Act: -0.0000

Data Index: 240401 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1118270 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1561072 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4013. Min Act: -0.0000

Data Index: 498920 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1269406 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1405876 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3463. Min Act: -0.0000

Data Index: 863663 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3042. Min Act: -0.0000

Data Index: 163411 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1545358 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1441604 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1504989 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1284134 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3423. Min Act: -0.0000

Data Index: 983751 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1462935 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1602203 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1213383 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1501597 (Python Code)

Max Activating Token Index: 409

Text #19

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1256930 (C4 (Web Text))

Max Activating Token Index: 605