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

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

Neuron 5887 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: 2.8791. Min Range: -2.8791

Max Act: 2.8791. Min Act: -0.0000

Data Index: 814641 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.6025. Min Act: -0.0000

Data Index: 114124 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.3002. Min Act: -0.0000

Data Index: 1123946 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.4413. Min Act: -0.0000

Data Index: 505015 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.3797. Min Act: -0.0000

Data Index: 500063 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.2476. Min Act: -0.0000

Data Index: 1124833 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.3312. Min Act: -0.0000

Data Index: 660335 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.3364. Min Act: -0.0000

Data Index: 944358 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.3350. Min Act: -0.0000

Data Index: 741389 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.2723. Min Act: -0.0000

Data Index: 582685 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.2660. Min Act: -0.0000

Data Index: 1188247 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.1098. Min Act: -0.0000

Data Index: 404460 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.3171. Min Act: -0.0000

Data Index: 288061 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.3321. Min Act: -0.0000

Data Index: 335533 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.2039. Min Act: -0.0000

Data Index: 935792 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 2.8791. Min Range: -2.8791

Max Act: 1.9810. Min Act: -0.0000

Data Index: 1223188 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.2973. Min Act: -0.0000

Data Index: 1281193 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.1614. Min Act: -0.0000

Data Index: 1228857 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.1804. Min Act: -0.0000

Data Index: 969869 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.1598. Min Act: -0.0000

Data Index: 416627 (C4 (Web Text))

Max Activating Token Index: 154