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

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

Neuron 3969 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2114. Min Range: -2.2114

Max Act: 2.2114. Min Act: -0.0000

Data Index: 536685 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 2.2114. Min Range: -2.2114

Max Act: 2.1093. Min Act: -0.0000

Data Index: 1032734 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.8491. Min Act: -0.0000

Data Index: 217850 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.8147. Min Act: -0.0000

Data Index: 387705 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.7632. Min Act: -0.0000

Data Index: 721304 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.6608. Min Act: -0.0000

Data Index: 106458 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.6233. Min Act: -0.0000

Data Index: 778388 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.8022. Min Act: -0.0000

Data Index: 869562 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.7978. Min Act: -0.0000

Data Index: 907202 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.6799. Min Act: -0.0000

Data Index: 555071 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.7647. Min Act: -0.0000

Data Index: 1218276 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.6348. Min Act: -0.0000

Data Index: 248716 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.6370. Min Act: -0.0000

Data Index: 188129 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.6094. Min Act: -0.0000

Data Index: 708332 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1268848 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.5785. Min Act: -0.0000

Data Index: 1108666 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.5778. Min Act: -0.0000

Data Index: 538934 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.5375. Min Act: -0.0000

Data Index: 90030 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1182376 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 2.2114. Min Range: -2.2114

Max Act: 1.4404. Min Act: -0.0000

Data Index: 75759 (C4 (Web Text))

Max Activating Token Index: 184