Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3179 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3278. Min Act: -0.0001

Data Index: 1022184 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3668. Min Act: -0.0001

Data Index: 188704 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2967. Min Act: -0.0001

Data Index: 712274 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2601. Min Act: -0.0001

Data Index: 152948 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1828. Min Act: -0.0001

Data Index: 638166 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2339. Min Act: -0.0001

Data Index: 223350 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2477. Min Act: -0.0001

Data Index: 1258670 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1952. Min Act: -0.0001

Data Index: 236865 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2700. Min Act: -0.0001

Data Index: 612117 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2539. Min Act: -0.0001

Data Index: 518617 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1200. Min Act: -0.0001

Data Index: 869845 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1762. Min Act: -0.0001

Data Index: 112047 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1198. Min Act: -0.0001

Data Index: 926494 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2410. Min Act: -0.0001

Data Index: 150387 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1273. Min Act: -0.0001

Data Index: 1163085 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0808. Min Act: -0.0001

Data Index: 194544 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1470. Min Act: -0.0001

Data Index: 752257 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1227. Min Act: -0.0001

Data Index: 960624 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1145. Min Act: -0.0001

Data Index: 265291 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0955. Min Act: -0.0001

Data Index: 96402 (C4 (Web Text))

Max Activating Token Index: 282