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

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

Neuron 610 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.8040. Min Act: -0.0002

Data Index: 181715 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.7442. Min Act: -0.0002

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.5632. Min Act: -0.0002

Data Index: 864946 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.5499. Min Act: -0.0002

Data Index: 1266549 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.5079. Min Act: -0.0002

Data Index: 1210009 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.4290. Min Act: -0.0002

Data Index: 557040 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.4915. Min Act: -0.0002

Data Index: 1179628 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.4753. Min Act: -0.0002

Data Index: 1102342 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.3949. Min Act: -0.0002

Data Index: 599402 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.3435. Min Act: -0.0002

Data Index: 1338213 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.4277. Min Act: -0.0003

Data Index: 908187 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.2894. Min Act: -0.0002

Data Index: 342665 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.2791. Min Act: -0.0002

Data Index: 1212637 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.3711. Min Act: -0.0002

Data Index: 1164148 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.3276. Min Act: -0.0002

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.3334. Min Act: -0.0002

Data Index: 462615 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.2729. Min Act: -0.0002

Data Index: 46004 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.3241. Min Act: -0.0002

Data Index: 679895 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.3233. Min Act: -0.0002

Data Index: 1151322 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 2.8040. Min Range: -2.8040

Max Act: 2.2749. Min Act: -0.0002

Data Index: 1021183 (C4 (Web Text))

Max Activating Token Index: 112